6 papers
When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
Jiakang Wang, Runze Liu, Qingpeng Cai +7
Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimiz…
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
Jiakang Wang, Runze Liu, Fuzheng Zhang +3
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, e…
Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors
Zhiwei Zhang, Fei Zhao, Rui Wang +6
Large language models (LLMs) can call tools effectively, yet they remain brittle in multi-turn execution: after a tool-call error, smaller models often fall into repetitive invalid…
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Runze Liu, Jiakang Wang, Yuling Shi +11
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more…
Data Metabolism: An Efficient Data Design Schema For Vision Language Model
Jingyuan Zhang, Hongzhi Zhang, Zhou Haonan +7
Data curation plays a crucial role in training powerful Visual Language Models (VLMs). In this work, we introduce the concept of Data Metabolism and present our data-centric framew…
Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Models
Xingguang Ji, Jiakang Wang, Hongzhi Zhang +6
With the development of Multimodal Large Language Models (MLLMs), numerous outstanding accomplishments have emerged within the open-source community. Due to the complexity of creat…