English
Related papers

Related papers: wd1: Weighted Policy Optimization for Reasoning in…

200 papers

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…

Artificial Intelligence · Computer Science 2025-10-06 Tianren Ma , Mu Zhang , Yibing Wang , Qixiang Ye

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Machine Learning · Computer Science 2024-05-31 Zeyu Fang , Tian Lan

Preference-based finetuning of vision--language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as \textbf{learning-dynamics--aware optimization} and…

Machine Learning · Computer Science 2025-10-15 Jusheng Zhang , Kaitong Cai , Jing Yang , Keze Wang

Reinforcement learning algorithms based on Q-learning are driving Deep Reinforcement Learning (DRL) research towards solving complex problems and achieving super-human performance on many of them. Nevertheless, Q-Learning is known to be…

Machine Learning · Computer Science 2022-06-14 Andrea Cini , Carlo D'Eramo , Jan Peters , Cesare Alippi

In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities,…

Machine Learning · Computer Science 2025-11-13 Yunchang Ma , Tenglong Liu , Yixing Lan , Xin Yin , Changxin Zhang , Xinglong Zhang , Xin Xu

Large language models (LLMs) excel at general mathematical reasoning but fail catastrophically on specialized technical mathematics. In wireless communications, where problems require precise manipulation of information-theoretic bounds,…

Machine Learning · Computer Science 2025-09-30 Xin Li , Mengbing Liu , Yiyang Zhu , Wenhe Zhang , Li Wei , Jiancheng An , Chau Yuen

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection.…

Robotics · Computer Science 2025-09-30 Rushuai Yang , Hangxing Wei , Ran Zhang , Zhiyuan Feng , Xiaoyu Chen , Tong Li , Chuheng Zhang , Li Zhao , Jiang Bian , Xiu Su , Yi Chen

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

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Machine Learning · Computer Science 2024-11-05 Shengchao Hu , Wanru Zhao , Weixiong Lin , Li Shen , Ya Zhang , Dacheng Tao

Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail. This lack of variance eliminates crucial learning signals.…

Machine Learning · Computer Science 2026-05-08 Xinyu Lu , Kaiqi Zhang , Jinglin Yang , Boxi Cao , Yaojie Lu , Hongyu Lin , Min He , Xianpei Han , Le Sun

Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function…

Machine Learning · Computer Science 2023-08-29 Zhendong Wang , Jonathan J Hunt , Mingyuan Zhou

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation,…

Robotics · Computer Science 2026-03-23 Zhennan Jiang , Kai Liu , Yuxin Qin , Shuai Tian , Yupeng Zheng , Mingcai Zhou , Chao Yu , Haoran Li , Dongbin Zhao

Large language models (LLMs) continue to struggle with mathematical reasoning, and common post-training pipelines often reduce each generated solution to a binary outcome: correct or incorrect. This perspective is limiting in practice, as…

Machine Learning · Computer Science 2026-04-15 Haocheng Lu , Minjun Zhu , Henry Yu

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Machine Learning · Computer Science 2024-12-17 Zhao Shan , Chenyou Fan , Shuang Qiu , Jiyuan Shi , Chenjia Bai

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

Machine Learning · Computer Science 2026-05-21 Haitong Ma , Ofir Nabati , Aviv Rosenberg , Bo Dai , Oran Lang , Craig Boutilier , Na Li , Shie Mannor , Lior Shani , Guy Tenneholtz

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

Computation and Language · Computer Science 2026-05-13 Miguel Moura Ramos , Duarte M. Alves , André F. T. Martins

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and…

Machine Learning · Computer Science 2025-09-24 Ranfei Chen , Ming Chen

Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow…

Machine Learning · Computer Science 2024-03-18 Huayu Chen , Cheng Lu , Zhengyi Wang , Hang Su , Jun Zhu

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Cryptography and Security · Computer Science 2025-07-08 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino

Masked diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. While reinforcement learning (RL) methods have recently been adapted to dLLM fine-tuning, their objectives typically depend on…

Machine Learning · Computer Science 2026-05-20 Yuyuan Chen , Shiyi Wang , Peter Potaptchik , Jaeyeon Kim , Michael S. Albergo