7 papers
Reinforcement Learning with Robust Rubric Rewards
Ya-Qi Yu, Hao Wang, Fangyu Hong +15
While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi…
Visual Preference Optimization with Rubric Rewards
Ya-Qi Yu, Fangyu Hong, Xiangyang Qu +15
The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often…
Concise Reasoning in the Lens of Lagrangian Optimization
Chengqian Gao, Haonan Li, Taylor W. Killian +6
Concise reasoning in large language models seeks to generate only essential intermediate steps needed to arrive at a final answer, thereby alleviating issues of overthinking. Most…
K2-Think: A Parameter-Efficient Reasoning System
Zhoujun Cheng, Richard Fan, Shibo Hao +28
K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1.…
Hawkeye:Efficient Reasoning with Model Collaboration
Jianshu She, Zhuohao Li, Zhemin Huang +4
Chain-of-Thought (CoT) reasoning has demonstrated remarkable effectiveness in enhancing the reasoning abilities of large language models (LLMs). However, its efficiency remains a c…
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Zhoujun Cheng, Shibo Hao, Tianyang Liu +21
Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our…