Signed Rectified Flow: Negativity-Controlled Generation
cs.LG, cs.CV
Submitted: 2026-07-20
Updated: 2026-11-08
Terminology
Sources
- Finetuned Language Models Are Zero-Shot Learners
- Multitask Prompted Training Enables Zero-Shot Task Generalization
- Classifier-Free Diffusion Guidance
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- Momentum Guidance: Plug-and-Play Guidance for Flow Models
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Constitutional AI: Harmlessness from AI Feedback
- Aligning Text-to-Image Models using Human Feedback
- Score-Based Generative Modeling through Stochastic Differential Equations
- Denoising Diffusion Implicit Models
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Rectified Flow: A Marginal Preserving Approach to Optimal Transport
- Flow Matching for Generative Modeling
- Building Normalizing Flows with Stochastic Interpolants
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
- Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
- CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- 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