activity
20242026
most citedRethinking Entropy Regularization in Large Reasoning Models

1 citations · 1 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL2026

Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?

Guanxu Chen, Dongrui Liu, Jing Shao

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped T…

cs.LG20251 cited

Rethinking Entropy Regularization in Large Reasoning Models

Yuxian Jiang, Yafu Li, Guanxu Chen +3

Reinforcement learning with verifiable rewards (RLVR) has shown great promise in enhancing the reasoning abilities of large reasoning models (LRMs). However, it suffers from a crit…

cs.AI2025

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models

Guanxu Chen, Yafu Li, Yuxian Jiang +6

Reinforcement Learning with Verifiable Rewards (RLVR) for large language models (LLMs) has achieved remarkable progress in enhancing LLMs' reasoning capabilities on tasks with clea…

cs.CL2025

Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step

Jingyi Yang, Guanxu Chen, Xuhao Hu +1

Masked diffusion language models (MDLMs) have recently emerged as a promising alternative to autoregressive (AR) language models, offering properties such as parallel decoding, fle…

cs.AI2025

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement

Yuanzhe Shen, Zisu Huang, Zhengkang Guo +5

The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety chall…

cs.AI2025

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law

Shanghai AI Lab, :, Yicheng Bao +115

We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…