collaborators

9 papers

cs.CL2026

Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation

Yanjiang Liu, Jie Lou, Xinyan Guan +7

On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identif…

cs.CL2026

Coupled Variational Reinforcement Learning for Language Model General Reasoning

Xueru Wen, Jie Lou, Yanjiang Liu +6

While reinforcement learning has achieved impressive progress in language model reasoning, it is constrained by the requirement for verifiable rewards. Recent verifier-free RL meth…

cs.AI2026

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing

Xueru Wen, Jie Lou, Xinyu Lu +5

As AI capabilities increasingly surpass human proficiency in complex tasks, current alignment techniques, including SFT and RLHF, face fundamental challenges in ensuring reliable o…

cs.CV2025

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Qianhao Yuan, Qingyu Zhang, Yanjiang Liu +6

Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-w…

cs.CR2025

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning

Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1

The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…

cs.CL2025

Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction

Tianyun Zhong, Guozhao Mo, Yanjiang Liu +9

With the emergence of large language models (LLMs), there is an expectation that LLMs can effectively extract explicit information from complex real-world documents (e.g., papers,…