English
Related papers

Related papers: DACA-GRPO: Denoising-Aware Credit Assignment for R…

200 papers

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

Machine Learning · Computer Science 2026-05-26 Fei Ding , Yongkang Zhang , Youwei Wang , Zijian Zeng

Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this…

Machine Learning · Computer Science 2026-03-05 Haodong Zhu , Yangyang Ren , Yanjing Li , Mingbao Lin , Linlin Yang , Xuhui Liu , Xiantong Zhen , Haiguang Liu , Baochang Zhang

Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action…

Robotics · Computer Science 2025-10-01 Zezeng Li , Rui Yang , Ruochen Chen , ZhongXuan Luo , Liming Chen

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided…

Machine Learning · Computer Science 2026-04-23 Fangjun Hu , Guangkuo Liu , Yifan F. Zhang , Xun Gao

Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise. When agents share a common reward, each agent's learning signal is computed from a shared return that depends on all agents, so the…

Multiagent Systems · Computer Science 2026-05-06 Shan Yang , Yang Liu

Modern reasoning agents are increasingly evaluated on their ability to generate multiple valid solution paths, plans, or tool-use traces for a given input. Standard reward-maximizing RL tends to collapse onto the most easily reinforced…

Automated grading of Knee Osteoarthritis (KOA) from radiographs is challenged by significant inter-observer variability and the limited robustness of deep learning models, particularly near critical decision boundaries. To address these…

Image and Video Processing · Electrical Eng. & Systems 2025-06-23 Zhe Wang , Yuhua Ru , Aladine Chetouani , Tina Shiang , Fang Chen , Fabian Bauer , Liping Zhang , Didier Hans , Rachid Jennane , William Ewing Palmer , Mohamed Jarraya , Yung Hsin Chen

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

Computation and Language · Computer Science 2026-05-19 Fanqin Zeng , Feng Hong , Geng Yu , Huangjie Zheng , Xiaofeng Cao , Ya Zhang , Bo Han , Yanfeng Wang , Jiangchao Yao

Diffusion models can be improved with additional guidance towards more effective representations of input. Indeed, prior empirical work has already shown that aligning internal representations of the diffusion model with those of…

Machine Learning · Computer Science 2025-10-14 Chenyu Wang , Cai Zhou , Sharut Gupta , Zongyu Lin , Stefanie Jegelka , Stephen Bates , Tommi Jaakkola

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jaxon Zhang , Binxin Yang , Hubery Yin , Chen Li , Jing Lyu

To make reinforcement learning more sample efficient, we need better credit assignment methods that measure an action's influence on future rewards. Building upon Hindsight Credit Assignment (HCA), we introduce Counterfactual Contribution…

Machine Learning · Computer Science 2023-11-01 Alexander Meulemans , Simon Schug , Seijin Kobayashi , Nathaniel Daw , Gregory Wayne

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Jing Wang , Jiajun Liang , Jie Liu , Henglin Liu , Gongye Liu , Jun Zheng , Wanyuan Pang , Ao Ma , Zhenyu Xie , Xintao Wang , Meng Wang , Pengfei Wan , Xiaodan Liang

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of…

Reinforcement learning (RL) allows vision-language-action (VLA) policies to generalize beyond their training distribution by optimizing directly for task success, but post-training is computationally expensive. A natural response has been…

Machine Learning · Computer Science 2026-05-18 Vaidehi Bagaria , Nikshep Grampurohit , Pulkit Verma

Understanding causal dependencies in observational data is critical for informing decision-making. These relationships are often modeled as Bayesian Networks (BNs) and Directed Acyclic Graphs (DAGs). Existing methods, such as NOTEARS and…

Machine Learning · Computer Science 2026-04-03 Hao Zhu , Di Zhou , Donna Slonim

This study addresses gender bias in image generation models using Reinforcement Learning from Artificial Intelligence Feedback (RLAIF) with a novel Denoising Diffusion Policy Optimization (DDPO) pipeline. By employing a pretrained stable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Xin Chen , Virgile Foussereau

Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption. We introduce \textbf{TreeGRPO}, a novel RL…

Machine Learning · Computer Science 2025-12-10 Zheng Ding , Weirui Ye

Our preliminary experiments on gym-DSSAT maize irrigation tasks revealed that +/-2 degrees C temperature noise causes an 11.9% reduction in economic returns for PPO policies trained under clean conditions - a systematic robustness deficit…

Machine Learning · Computer Science 2026-05-19 Wu Yang
‹ Prev 1 4 5 6 7 8 10 Next ›