5 papers
QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides
Zhengyang Zhuge, Hao Yu, Xin Wang +4
Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP…
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Hao Xiang, Qiaoyu Tang, Le Yu +8
Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior re…
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
Boyi Deng, Xu Wang, Yaoning Wang +15
Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspec…
Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
Xueyun Tian, Minghua Ma, Bingbing Xu +6
Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typicall…
X-Guard: Multilingual Guard Agent for Content Moderation
Bibek Upadhayay, Vahid Behzadan, Ph. D
Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety framew…