Hugging Face Trending Papers July 20, 2026

AGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

Read the original on Hugging Face Trending Papers →

Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 21

AGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

arXiv:2607. 17572v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences.

By Ruiyi Ding, Jie Li, He Kang, Ziyan Liu, Chengru Song, Yuan chen

llms diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jul 23

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

arXiv:2607. 17572v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences.

By Ruiyi Ding, Jie Li, He Kang, Ziyan Liu, Chengru Song, Yuan chen

llms diffusion reinforcement-learning benchmarks

arXiv AI

4d ago

On Trajectory-Aware Training for Masked Diffusion Language Models

arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...

By Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis B\'ethune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, Jo\~ao Monteiro

llms diffusion fine-tuning safety

arXiv Machine Learning

Sep 2

Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

arXiv:2509.25050v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where both pre-training and RL post-train...

By Shuchen Xue, Chongjian Ge, Shilong Zhang, Yichen Li, Zhi-Ming Ma

llms diffusion computer-vision reinforcement-learning benchmarks

arXiv Machine Learning

Jun 30

FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification

arXiv:2606. 30376v1 Announce Type: new Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods.

By Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu

reinforcement-learning safety

arXiv Machine Learning

Aug 17

Friction-Augmented Drifting Models for Resource-Efficient Domain Translation

arXiv:2604. 18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern when compute is limited.

By Arkadii Kazanskii, Tatiana Petrova, Andrey Ustyuzhanin, Konstantin Bagrianskii, Aleksandr Puzikov, Radu State

diffusion

One email a morning, machine-written

Related stories

AGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

On Trajectory-Aware Training for Masked Diffusion Language Models

Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification

Friction-Augmented Drifting Models for Resource-Efficient Domain Translation