Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field

arXiv:2605.16348 · cs.LG, cs.AI · Submitted 2026-05-08 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: AI Radio. Generated commentary on the latest Artificial Intelligence papers.

Tom: We're looking at the paper: "Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field".

Jane: Here's the gist of the paper. Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions.

Tom: Flow-Direct proposes a framework that guides the generation process via a persistent guidance field.

Jane: This guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions.

Tom: In practice, the field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples.

Paper summary: Jane: So, to wrap up, the "Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field" paper is proposing this persistent guidance field approach >

Tom: They are using feedback from external reward functions to guide pre-trained diffusion and flow models during inference by building a non-parametric estimator of that guidance field >

Lu: The main contribution is turning transient, localized feedback into a persistent structure that allows for efficient, reusable generation across multiple specific targets without needing repeated evaluations >

Meng: From an engineering standpoint, the fact that the cost scales linearly with the sample size and it's sampler-agnostic means we can actually integrate this into production pipelines more easily than methods that require retraining >

Tom: It’s about making training-free guidance practical by providing a stable, analytically derived way to transport from the noise distribution to the desired data distribution using an external signal >

Jane: For someone just listening, it means we might see generative models steer themselves toward specific complex outcomes with less direct manual intervention during the final generation step >

Conclusion: Tom: So we've been talking about how these new models can use external feedback to get better results, and today we're looking at this paper called Flow-Direct by some researchers.

Jane: They’re calling it "Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field". It sounds like they're tackling the problem of steering these diffusion and flow models with feedback without needing to retrain everything every time.

Lu: What they did is build this guidance field, which is essentially a mathematical map derived from comparing the model's base output distribution against what you want the reward function to produce.

Meng: So instead of just using that feedback once and forgetting it, they create a persistent estimator from all those reward samples. That means every time you test something, it helps build this map for future generations.

Tom: Right, so it's like the model keeps learning where the "good" stuff is based on all its past failures or successes with that external feedback loop. It's about making that guidance process efficient and not throwing away information.

Jane: The real kicker here, as I see it, is how this map becomes reusable. Once they’ve built this field for one specific goal, they can use it to generate brand new samples for that same goal without having to go back and re-evaluate the reward function repeatedly.

Lu: And if you have several different targets—say you want image A *and* image B—they can actually combine those guidance maps linearly to get something that hits both targets at once. That's pretty ambitious for a method like this.

Meng: From an engineering standpoint, I'm looking at the scaling. They say the memory and time needed for this field grow in a linear way with how many samples you collect, which is good news when you're trying to run things on actual hardware.

Tom: It does sound like it handles the feedback efficiently by aggregating everything persistently instead of just using it transiently. That aggregation is key to making the whole process stable and predictable for deployment.

Jane: So, to put it simply, this framework takes a messy, external reward signal and turns it into a persistent set of instructions that guides the model through its entire generation process smoothly.

Tom: It seems like they've managed to make training-free guidance practical by focusing on building that guidance field in a way that’s both robust and scalable for multiple objectives.

Jane: What this really means for us is we might see AI systems steer themselves toward very specific, complex creative or technical goals with less direct manual tuning during the generation step.

Tom: It's moving the needle from just training a model to making it actively optimize its own output based on real-world performance feedback.

Jane: Next up, we'll look at what this means for different types of generative models and where the limits of this method lie.

Kim Yong Tan, Yueming Lyu, Ivor Tsang, Yew-Soon Ong

College of Computing and Data Science, Nanyang Technological University · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore

cs.LG, cs.AI

Submitted: 2026-05-08

Updated: 2026-11-06

License: http://creativecommons.org/licenses/by/4.0/

Importance score: 100/100

The gist: Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions.

Key concepts

Training-free Guidance
This technique allows pre-trained models to optimize their output based on external reward signals without requiring additional training on those rewards. Instead of fine-tuning the model directly, it uses the reward feedback to guide the generation process during inference using a derived guidance field.
Guidance Field Construction
The core mechanism involves creating a persistent guidance field. Theoretically, this field is based on the log-density ratio between two distributions: the base distribution of the model and a reward-weighted target distribution. Practically, it is built as a non-parametric estimator using all accumulated samples from reward evaluations.
Feedback Efficiency and Persistence
Flow-Direct ensures high feedback efficiency because every sample used for evaluation contributes to refining a global guidance field. This prevents information loss by persistently aggregating all evaluated samples into an empirical dataset, allowing the model to benefit continuously from the collected rewards.
Reusability and Multi-Target Generation
The framework is reusable because the learned guidance field for one target can be reused for new samples of that target. Furthermore, guidance fields from different objectives can be linearly combined to generate samples that satisfy several targets simultaneously by constructing a mixed guidance field.

Terminology

Summary

Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. p. 0

Where the paper says it

sg {Lyu_Yueming,Ivor_Tsang}@cfar. sg Abstract Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions.

Flow-Direct proposes a framework that guides the generation process via a persistent guidance field. p. 0
Where the paper says it

However, existing methods are feedback-inefficient because reward feedback is used only transiently to inform a localized gradient approximation or a discrete search decision, and is subsequently discarded. To address this limitation, we propose Flow-Direct, a framework that guides the generation process via a persistent guidance field.

This guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions. p. 0
Where the paper says it

To address this limitation, we propose Flow-Direct, a framework that guides the generation process via a persistent guidance field. Theoretically, this guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions; it transports the pre-trained distribution to the target distribution.

In practice, the field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples. p. 0
Where the paper says it

Theoretically, this guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions; it transports the pre-trained distribution to the target distribution. In practice, the field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples.

Core Mechanism of Guidance Construction

The guidance field is theoretically derived from the log-density ratio between the base and reward-weighted target distributions. In practice, this field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples. p. 0

Where the paper says it

Theoretically, this guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions; it transports the pre-trained distribution to the target distribution. In practice, the field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples.

The guidance field is constructed by approximating the posterior expectation using the non-parametric estimator given in Proposition 1. p. 3
Where the paper says it

Geometrically, it is a vector pointing from the base data towards the target data. In practice, we implement the guidance field by approximating the posterior expectation using the non-parametric estimator given in Proposition 1 with the derivation provided in Appendix A: Proposition 1 (Estimator for Posterior Expectation) Let D = {x i 1} N i=1 be a dataset where x i 1 iid∼ p base 1 (x1).

This estimator converges to the true posterior expectation as the dataset size grows to infinity. p. 3
Where the paper says it

Under the flow matching framework, for any xt with t ∈ [0, 1), the posterior expectation can be estimated by: X N i=1 softmax i ′∈[N] − ∥xt − txi ′ 1 ∥ 2 2(1 − t) 2 ! i | {z } pˆ1(x1=x i 1 |xt) x i 1 N→∞ −−−−→ Ep1 [x1|xt], (7) and the estimator converges to the true posterior expectation as the dataset size grows to infinity.

The practical implementation of the guidance field is given by Equation (8). p. 5
Where the paper says it

i # x i 1 (16) where α also control the strength of the guidance signal. Furthermore, given a collection of K datasets {Dk all} K k=1 optimized for distinct rewards, we can naturally extend this formulation to achieve 5See Equation (16-practical) for the corresponding practical implementation.

Feedback Efficiency and Persistence

Flow-Direct is highly feedback-efficient because every evaluated sample is used to refine the global guidance field. Rather than utilizing reward feedback transiently, the non-parametric implementation allows us to aggregate the evaluated samples persistently, ensuring no reward information loss. p. 1

Where the paper says it

In practice, the guidance field is implemented as a nonparametric estimator constructed from the reward-evaluated samples. Flow-Direct is highly feedback-efficient because rather than utilizing reward feedback transiently, the non-parametric implementation allows us to aggregate the evaluated samples persistently, ensuring no reward-information loss.

Over the course of the optimization process, all reward-evaluated samples are appended to a growing empirical dataset. p. 1
Where the paper says it

Flow-Direct is highly feedback-efficient because rather than utilizing reward feedback transiently, the non-parametric implementation allows us to aggregate the evaluated samples persistently, ensuring no reward-information loss. Over the course of the optimization process, all reward-evaluated samples are appended to a growing empirical dataset.

This persistent formulation yields two major advantages. p. 0
Where the paper says it

As more samples are collected during optimization, this empirical guidance field becomes increasingly accurate. This persistent formulation yields two major advantages.

Reusability and Multi-Target Generation

Furthermore, this framework is naturally reusable. Once a labeled dataset is collected for a specific target objective, its corresponding empirical guidance field can be reused to generate novel target samples without further reward evaluations. p. 1

Where the paper says it

Furthermore, this framework is naturally reusable. Once a labeled dataset is collected for a specific target objective, its corresponding empirical guidance field can be reused to generate novel target samples without further reward evaluations.

Additionally, the non-parametric estimators learned from distinct objectives can be linearly combined to produce samples that simultaneously satisfy multiple targets. p. 1
Where the paper says it

Once a labeled dataset is collected for a specific target objective, its corresponding empirical guidance field can be reused to generate novel target samples without further reward evaluations. Additionally, the non-parametric estimators learned from distinct objectives can be linearly combined to produce samples that simultaneously satisfy multiple targets.

This is achieved by constructing a mixed guidance field by linearly combining the guidance fields associated with the K targets. p. 6
Where the paper says it

compositional multi-target generation. Specifically, we construct a mixed guidance field by linearly combining the guidance fields associated with the K targets: ∆mix(xt) = X K k=1 ∆(xt; D k all, αk), (17) where each αk controls the guidance strength and trade-off of each k-th objective.

Performance and Scalability

Flow-Direct consistently achieves the highest reward across all five reward functions. Table 2 shows the efficiency gain factor of Flow-Direct over each baseline. p. 7

Where the paper says it

Flow-Direct consistently achieves the highest reward across all five reward functions. Table 2 shows the efficiency gain factor, computed as 1600 divided by the number of reward evaluations Flow-Direct needed to match or surpass each baseline.

The computational time and memory consumption of the guidance field scale linearly with the dataset size N. p. 7
Where the paper says it

Additionally, we analyze the computational overhead in Appendix C. The results show that the computational time and memory consumption of the guidance field ∆(xt) both scale linearly with the dataset size N.

Both variants achieve comparable rewards across all reward functions, and both outperform all baselines. p. 7
Where the paper says it

In Table 3, we further compare Flow-Direct with the SDE sampler and the deterministic ODE sampler under the same reward-evaluation budget. The two variants achieve comparable rewards across reward functions, and both outperform all baselines, indicating that Flow-Direct is flexible and sampler-agnostic.

Flow-Direct is compatible with both deterministic ODE and stochastic SDE samplers. p. 7
Where the paper says it

Results show that increasing either the optimization steps or the batch size yields a steady and stable improvement in the final reward, demonstrating the stability and scalability of Flow-Direct. Furthermore, unlike baseline methods, our formulation is compatible with both deterministic ODE and stochastic SDE samplers.

The framework is tuning-free as it relies on a closed-form derivation of the guidance field. p. 6
Where the paper says it

Tuning-Free. Flow-Direct (Algorithm 1) relies on a closed-form derivation of the guidance field.

The formulation is sampler-agnostic because it directly modifies the continuous vector field. p. 6
Where the paper says it

Sampler-Agnostic. Flow-Direct directly modifies the continuous vector field, thus it is fundamentally agnostic to the choice of numerical sampler.

The framework demonstrates superior effectiveness, scalability, and robust performance across multiple domains compared to existing methods. p. 1
Where the paper says it

Moreover, multiple empirical fields can be linearly combined to generate samples that simultaneously satisfy multiple objectives. • Finally, we conduct comprehensive experiments on both image and 3D generation tasks, indicating Flow-Direct’s superior effectiveness, scalability, and robust performance across multiple domains compared to existing methods.

The authors also discuss the limitations of the work performed. p. 2
Where the paper says it

Iterating this update from t = 0 to t = 1 produces a final sample x1 ∼ p θ 1 (x1) from the learned data distribution. In this work, we treat the numerical update operator step as a black-box sampler, which may be instantiated by more advanced ODE or SDE solvers, and we focus solely on modifying the vector field vt.

The paper does not release any new datasets or pre-trained models. p. 0
Where the paper says it

sg {Lyu_Yueming,Ivor_Tsang}@cfar. sg Abstract Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions.

It is noted that increasing either the optimization steps or the batch size yields a steady and stable improvement in the final reward. p. 7
Where the paper says it

We conduct ablation study on these parameters in Appendix C. Results show that increasing either the optimization steps or the batch size yields a steady and stable improvement in the final reward, demonstrating the stability and scalability of Flow-Direct.

The research conforms with the NeurIPS Code of Ethics. p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

The authors cite original papers for all pre-trained models and baseline methods used in the paper. p. 0
Where the paper says it

sg Abstract Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, existing methods are feedback-inefficient because reward feedback is used only transiently to inform a localized gradient approximation or a discrete search decision, and is subsequently discarded.

p. 0
Where the paper says it

sg Abstract Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, existing methods are feedback-inefficient because reward feedback is used only transiently to inform a localized gradient approximation or a discrete search decision, and is subsequently discarded.

The code is provided as the supplemental materials, and we will release the source code upon publication. p. 7
Where the paper says it

For the aerodynamic optimization, we repeat each experiment over three seeds. We will release the source code upon publication.

All pre-trained models and baseline methods used in the paper are properly cited, and we use them in accordance with their respective public release licenses and intended research use. p. 0
Where the paper says it

sg Abstract Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, existing methods are feedback-inefficient because reward feedback is used only transiently to inform a localized gradient approximation or a discrete search decision, and is subsequently discarded.

The authors cite original papers for all pre-trained models and baseline methods used in the paper. The paper does not involve any crowdsourcing or research with human subjects. p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

The paper does not involve any crowdsourcing nor research with human subjects. p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

p. 0
Where the paper says it

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Kim Yong Tan 1 Yueming Lyu 2,3∗ Ivor Tsang1,2,3 Yew-Soon Ong1,2,3 1College of Computing and Data Science, Nanyang Technological University, Singapore 2Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 3 Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore {KIMYONG001,ASYSOng}@ntu. sg {Lyu_Yueming,Ivor_Tsang}@cfar.

The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects. The paper does not involve any crowdsourcing nor research with human subjects. The paper does not involve any crowdsourcing or research with human subjects <ref:2605.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Feedback-efficient guidance field construction allows for persistent aggregation of reward information, ensuring no reward information is wasted, which enables highly accurate guidance as more samples are collected.

  2. The framework is naturally reusable because once a labeled dataset is collected, it can steer the flow model to generate novel target samples without requiring further reward evaluations.

  3. Distinct guidance fields from different objectives can be linearly combined to produce samples that simultaneously satisfy multiple targets, offering multi-objective generation capabilities without additional reward evaluations.

  4. The guidance field is analytically derived as the log-density ratio between the base and reward-weighted target distributions, providing a theoretically sound mechanism for transporting the pre-trained distribution to the target distribution.

  5. The implementation uses a non-parametric estimator constructed from accumulated samples, which ensures that every evaluated sample is used to refine the global guidance field, leading to an increasingly accurate approximation as the dataset expands.

  6. Flow-Direct is sampler agnostic, meaning it directly modifies the continuous vector field, ensuring stable performance regardless of whether a deterministic ODE or stochastic SDE sampler is used during inference.

  7. The system can be tuned without complex optimization parameters; it is Tuning-Free, relying only on the reward evaluation budget (batch size N and optimization iterations L) for stability and scalability.

  8. The framework can achieve superior performance in various domains, as shown by its ability to consistently produce samples that strongly reflect the target reward while preserving the visual and structural quality across image alignment and 3D aerodynamic optimization.

Abstract

Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, existing methods are feedback-inefficient because reward feedback is used only transiently to inform a localized gradient approximation or a discrete search decision, and is subsequently discarded. To address this limitation, we propose Flow-Direct, a framework that guides the generation process via a persistent guidance field. Theoretically, this guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions; it transports the pre-trained distribution to the target distribution. In practice, the field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples. As more samples are collected during optimization, this empirical guidance field becomes increasingly accurate. This persistent formulation yields two major advantages. First, Flow-Direct is highly feedback-efficient: because every evaluated sample is used to refine the global guidance field, no reward information is wasted. Second, the framework is naturally reusable: once optimization is complete, the collected dataset defines a reusable guidance field for generating novel target samples without additional reward evaluations, and distinct guidance fields can be combined to generate samples that simultaneously satisfy multiple objectives.

Sources

Related papers