5 papers
GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation
Zeyu Yan, Guanghao Zhou, Minghui Qiu +2
Recent advances in large reasoning models (LRMs) have made machine unlearning more challenging, as protected facts or unsafe rationales may surface in intermediate chain-of-thought…
Valley3: Scaling Omni Foundation Models for E-commerce
Zeyu Chen, Guanghao Zhou, Qixiang Yin +6
In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understanding and reasoning capabilitie…
When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
Mingyuan Fan, Weiguang Han, Daixin Wang +3
Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domain…
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
Guanghao Zhou, Panjia Qiu, Cen Chen +4
The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabiliti…
Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
Guanghao Zhou, Panjia Qiu, Cen Chen +4
The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. Whil…