collaborators

6 papers

cs.LG2026

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Yuqiao Tan, Minzheng Wang, Shizhu He +6

Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-b…

cs.LG2026

From to : Investigating Reinforcement Learning in Pre-train Space

Yuqiao Tan, Minzheng Wang, Bo Liu +5

While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), its potential is fundamentally b…

cs.CV2026

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

Xiangyu Zhao, Peiyuan Zhang, Junming Lin +7

Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics…

cs.AI2026

The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context

Xiaoyuan Liu, Tian Liang, Dongyang Ma +4

In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve-…

cs.AI2026

Free(): Learning to Forget in Malloc-Only Reasoning Models

Yilun Zheng, Dongyang Ma, Tian Liang +5

Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it.…

cs.CV2025

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Xiangyu Zhao, Junming Lin, Tianhao Liang +11

While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reas…