English
Related papers

Related papers: Flash-GRPO: Efficient Alignment for Video Diffusio…

200 papers

This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Zhanhao Liang , Tao Yang , Jie Wu , Chengjian Feng , Liang Zheng

Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Yuanhao Cai , Kunpeng Li , Menglin Jia , Jialiang Wang , Junzhe Sun , Feng Liang , Weifeng Chen , Felix Juefei-Xu , Chu Wang , Ali Thabet , Xiaoliang Dai , Xuan Ju , Alan Yuille , Ji Hou

Medical artificial intelligence systems have achieved remarkable diagnostic capabilities, yet they consistently exhibit performance disparities across demographic groups, causing real-world harm to underrepresented populations. While recent…

Machine Learning · Computer Science 2025-10-24 Shiqi Dai , Wei Dai , Jiaee Cheong , Paul Pu Liang

Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical success, they exhibit structural mismatches between reward…

Machine Learning · Computer Science 2026-01-09 Aleksandar Fontana , Marco Simoni , Giulio Rossolini , Andrea Saracino , Paolo Mori

Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Existing works attempt to progressively narrow the search…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Junwen Pan , Qizhe Zhang , Rui Zhang , Ming Lu , Xin Wan , Yuan Zhang , Chang Liu , Qi She

Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Junhao Xia , Chaoyang Zhang , Yecheng Zhang , Chengyang Zhou , Zhichang Wang , Bochun Liu , Dongshuo Yin

Distributed training using multiple devices (e.g., GPUs) has been widely adopted for learning DNN models over large datasets. However, the performance of large-scale distributed training tends to be far from linear speed-up in practice.…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-05-19 Hanpeng Hu , Chenyu Jiang , Yuchen Zhong , Yanghua Peng , Chuan Wu , Yibo Zhu , Haibin Lin , Chuanxiong Guo

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end…

Computation and Language · Computer Science 2026-05-14 Siyuan Zhu , Chao Yu , Rongxin Yang , Zongkai Liu , Jinjun Hu , Qiwen Chen , Yibo Zhang

Diffusion probabilistic models have set a new standard for generative fidelity but are hindered by a slow iterative sampling process. A powerful training-free strategy to accelerate this process is Schedule Optimization, which aims to find…

Machine Learning · Computer Science 2026-05-20 Aihua Zhu , Rui Su , Qinglin Zhao , Li Feng , Meng Shen , Shibo He

Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However, its application to continuous control remains unexplored,…

Robotics · Computer Science 2025-07-29 Rajat Khanda , Mohammad Baqar , Sambuddha Chakrabarti , Satyasaran Changdar

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain…

Machine Learning · Computer Science 2026-04-14 Yang Zhao , Hepeng Wang , Xiao Ding , Yangou Ouyang , Bibo Cai , Kai Xiong , Jinglong Gao , Zhouhao Sun , Li Du , Bing Qin , Ting Liu

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiaze Li , Hao Yin , Haoran Xu , Boshen Xu , Wenhui Tan , Zewen He , Jianzhong Ju , Zhenbo Luo , Jian Luan

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Weiyue Zhao , Xin Li , Zhan Peng , Xianrui Luo , Xinyi Ye , Hao Lu , Zhiguo Cao

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveraging stochastic…

Machine Learning · Computer Science 2025-11-25 Yujie Zhou , Pengyang Ling , Jiazi Bu , Yibin Wang , Yuhang Zang , Jiaqi Wang , Li Niu , Guangtao Zhai

Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Zening Sun , Zhengpeng Xie , Lichen Bai , Shitong Shao , Shuo Yang , Zeke Xie

Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yibin Wang , Zhimin Li , Yuhang Zang , Yujie Zhou , Jiazi Bu , Chunyu Wang , Qinglin Lu , Cheng Jin , Jiaqi Wang

The development of video diffusion models unveils a significant challenge: the substantial computational demands. To mitigate this challenge, we note that the reverse process of diffusion exhibits an inherent entropy-reducing nature. Given…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Lingmin Ran , Mike Zheng Shou

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Artificial Intelligence · Computer Science 2026-03-06 Anisha Garg , Claire Zhang , Nishit Neema , David Bick , Ganesh Venkatesh , Joel Hestness

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zhaochong An , Orest Kupyn , Théo Uscidda , Andrea Colaco , Karan Ahuja , Serge Belongie , Mar Gonzalez-Franco , Marta Tintore Gazulla

Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular programs that mix together multiple LM calls with distinct…