Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
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 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. 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. 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. 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.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
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 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. 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). 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. 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.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
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 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. 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. As more samples are collected
during optimization, this empirical guidance field becomes increasingly accurate. This persistent formulation yields two major advantages.Where the paper says it
Where the paper says it
Where the paper says it
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 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. 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. 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.Where the paper says it
Where the paper says it
Where the paper says it
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 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. 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. 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. 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. Tuning-Free. Flow-Direct (Algorithm 1) relies on a closed-form derivation of the guidance field. Sampler-Agnostic. Flow-Direct directly modifies the continuous vector field, thus it is fundamentally
agnostic to the choice of numerical sampler. 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. 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. 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. 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. 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. 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. 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. For the aerodynamic
optimization, we repeat each experiment over three seeds. We will release the source code upon
publication. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
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
-
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. -
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.
-
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. -
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. -
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. -
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. -
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. -
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
- Movie Gen: A Cast of Media Foundation Models
- Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
- 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
- MatterGen: a generative model for inorganic materials design
- Evolvable Conditional Diffusion
- A General Framework for Inference-time Scaling and Steering of Diffusion Models
- Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
- Dynamic Search for Inference-Time Alignment in Diffusion Models
- Flow Matching for Generative Modeling
- Training Diffusion Models with Reinforcement Learning
- Gemma: Open Models Based on Gemini Research and Technology
- DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations
- On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
- An analytic theory of creativity in convolutional diffusion models
- Flow-GRPO: Training Flow Matching Models via Online RL
- Stochastic Sampling from Deterministic Flow Models
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
Related papers
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning
- Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine