arXiv:2608. 14430v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards.
By Yixian Xu, Yuanrui Zhang, Shengjie Luo, Liwei Wang, Di He
CAST introduces a reinforcement‑learning fine‑tuning framework for diffusion models that addresses three key limitations: it automatically selects the denoising window based on each model’s trajectory, decomposes prompts into verifiable semantic atoms via Causal Scene Graphs, and applies atom‑level rewards spatially weighted in the policy objective. The method is applied to FLUX.2‑dev and Qwen‑Image‑2512, yielding up to 3.07× improvement on the hardest GenEval 2 prompts compared with Flow‑GRPO while also enhancing overall generation quality.
By Shu Yu, Chaochao Lu
VaLoP introduces a new method for reward-guided diffusion called Value Gradient Lookahead and Pullback, which evaluates the value function at a less noisy state and pulls its gradient back to the current state to reduce posterior covariance errors. The approach unifies two common gradient estimators and adds a correction term computed with a single vector-Jacobian product, while VaLoP‑Fast amortizes this correction with a lightweight head trained on a single reward. Experiments across multiple models, rewards, and datasets show that both variants consistently outperform existing value‑gradient guidance, and VaLoP‑Fast achieves the highest success rates on robot policy benchmarks such as LIBERO and RoboCasa.
By Kwanyoung Kim
Routing Policy Optimization (RPO) introduces stochastic exploration within a diffusion visual generator by treating attention routing as a stochastic action. Instead of perturbing the entire reverse denoising trajectory, RPO samples key attention blocks at selected denoising levels, perturbs the transition velocity, and evaluates the perturbation with a score‑function objective. A two‑rollout estimator provides an advantage signal, and after training the model restores dense attention, yielding higher generation quality and nearly four times the training efficiency compared to Flow‑GRPO‑style methods.
The paper investigates how different estimators of the reverse Kullback–Leibler (KL) divergence used as a regularization term in reinforcement learning (RL) training of large language models (LLMs) affect training stability and downstream performance. By analyzing gradient bias across various estimator configurations, the authors demonstrate that biased gradients can cause training instabilities, while unbiased configurations improve performance on both in‑domain and out‑of‑domain tasks. Experiments on Qwen2.5‑7B, Llama‑3.1‑8B‑Instruct, and Qwen3‑4B‑Instruct‑2507 confirm these findings and show that KL regularization also stabilizes off‑policy RL training in asynchronous setups.
By Vedant Shah, Johan Obando-Ceron, Vineet Jain, Brian Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Esmeralda S. Whitammer, Moksh Jain, Siddarth Venkatraman, Aaron Courville
arXiv:2608.23664v1 Announce Type: cross
Abstract: Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing method...
By Jaemoo Choi, Wei Guo, Yuchen Zhu, Arash Vahdat, Molei Tao, Julius Berner, Yongxin Chen