activity
20242026
most citedChinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models

1 citations · 2 across the 7 of their papers we have counts for

collaborators

15 papers

cs.CL2026

CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria

Xinyu Hu, Yancheng He, Weixun Wang +6

Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, th…

cs.LG2026

One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning

Yiyuan Li, Zhen Huang, Yanan Wu +6

The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of…

cs.AI2025

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Weixun Wang, XiaoXiao Xu, Wanhe An +86

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its impo…

cs.LG2025

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning

Jiashun Liu, Johan Obando-Ceron, Han Lu +7

Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are…

cs.LG2025

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony

Han Lu, Zichen Liu, Shaopan Xiong +19

Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…

cs.LG2025

MeSH: Memory-as-State-Highways for Recursive Transformers

Chengting Yu, Xiaobo Shu, Yadao Wang +8

Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under matched compute, recursive mode…