3 citations · 7 across the 36 of their papers we have counts for
40 papers
From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations
Yixin Yang, Yue Wang, Fandong Meng +1
Large reasoning models generate reasoning trajectories token by token. At a given prefix, multiple next-token candidates may be plausible, yet shape subsequent reasoning and differ…
Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search
Jingyuan Ma, Lynx Aster, He Zhang +5
Long-horizon information-seeking agents often accumulate noisy or misleading context, causing early mistakes to persist and making recovery increasingly difficult. We introduce an…
From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learning
Yudong Wang, Zhe Yang, Wenhan Ma +6
Rewards that penalize unsupported claims can improve grounding in long-form generation, but they can also teach models to answer less. We study this refusal-to-richness trade-off i…
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Wenhan Ma, Jianyu Wei, Liang Zhao +10
Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains…
SenseJudge: Human-Centric Preference-Driven Judgment Framework
Rui Li, Junfeng Liu, Xiangwen Kong +2
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approach…
Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Bowen Ye, Rang Li, Qibin Yang +10
Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by…
HistLens: Mapping Idea Change across Concepts and Corpora
Yi Jing, Weiyun Qiu, Yihang Peng +1
Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical and social transformation.…
Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity
Di Zhang, Xun Wu, Shaohan Huang +9
Semi-structured N:M sparsity and low-bit quantization (e.g., 1.58-bit BitNet) are two promising approaches for improving the efficiency of large language models (LLMs), yet they ha…
Towards Better RL Training Data Utilization via Second-Order Rollout
Zhe Yang, Yudong Wang, Rang Li +1
Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by tra…
CoLT: Reasoning with Chain of Latent Tool Calls
Fangwei Zhu, Zhifang Sui
Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods have been proposed to accelerate the…
Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning
Yixin Yang, Qingxiu Dong, Zhifang Sui
Sampling-based decoding underlies complex reasoning in large language models (LLMs), where decoding strategies critically shape model behavior. Temperature- and truncation-based me…
TeachBench: A Syllabus-Grounded Framework for Evaluating Teaching Ability in Large Language Models
Zheng Li, Siyao Song, Jingyuan Ma +4
Large language models (LLMs) show promise as teaching assistants, yet their teaching capability remains insufficiently evaluated. Existing benchmarks mainly focus on problem-solvin…
GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation
Rang Li, Lei Li, Shuhuai Ren +10
Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language mod…
Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning
Yudong Wang, Zhe Yang, Wenhan Ma +2
While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical tr…
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
Wenhan Ma, Hailin Zhang, Liang Zhao +4
Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mech…
LLM-REVal: Can We Trust LLM Reviewers Yet?
Rui Li, Jia-Chen Gu, Po-Nien Kung +5
The rapid advancement of large language models (LLMs) has inspired researchers to integrate them extensively into the academic workflow, potentially reshaping how research is pract…
Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts
Di Zhang, Xun Wu, Shaohan Huang +6
Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reaso…
A Probabilistic Inference Scaling Theory for LLM Self-Correction
Zhe Yang, Yichang Zhang, Yudong Wang +3
Large Language Models (LLMs) have demonstrated the capability to refine their generated answers through self-correction, enabling continuous performance improvement over multiple r…
Reinforcement Pre-Training
Qingxiu Dong, Li Dong, Yao Tang +4
In this work, we introduce Reinforcement Pre-Training (RPT) as a new scaling paradigm for large language models and reinforcement learning (RL). Specifically, we reframe next-token…
HauntAttack: When Attack Follows Reasoning as a Shadow
Jingyuan Ma, Rui Li, Zheng Li +4
Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities a…
From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
Zhengyu Chen, Yudong Wang, Teng Xiao +5
Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors…
RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
Yixin Yang, Qingxiu Dong, Linli Yao +2
Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Cont…
Chain-of-Thought Tokens are Computer Program Variables
Fangwei Zhu, Peiyi Wang, Zhifang Sui
Chain-of-thoughts (CoT) requires large language models (LLMs) to generate intermediate steps before reaching the final answer, and has been proven effective to help LLMs solve comp…
Towards Harmonized Uncertainty Estimation for Large Language Models
Rui Li, Jing Long, Muge Qi +4
To facilitate robust and trustworthy deployment of large language models (LLMs), it is essential to quantify the reliability of their generations through uncertainty estimation. Wh…