10 citations · 11 across the 11 of their papers we have counts for
12 papers
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…
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…
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…
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,…
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…
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models
Qiao Liang, Yanjiang Liu, Weixiang Zhou +7
Does the prior knowledge of the vision encoder constrain the capability boundary of Multi-modal Large Language Models (MLLMs)? While most existing research treats MLLMs as unified…
SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
Qianhao Yuan, Yanjiang Liu, Yaojie Lu +4
Multimodal Large Language Models (MLLMs) mainly fall into two architectures, each involving a trade-off between training and inference efficiency: embedding space alignment (e.g.,…
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…
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Yanjiang Liu, Shuhen Zhou, Yaojie Lu +6
Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, l…
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
Xinyan Guan, Yanjiang Liu, Xinyu Lu +8
The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models…
Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting
Xinyan Guan, Yanjiang Liu, Hongyu Lin +4
Incorporating factual knowledge in knowledge graph is regarded as a promising approach for mitigating the hallucination of large language models (LLMs). Existing methods usually on…
Understanding Differential Search Index for Text Retrieval
Xiaoyang Chen, Yanjiang Liu, Ben He +2
The Differentiable Search Index (DSI) is a novel information retrieval (IR) framework that utilizes a differentiable function to generate a sorted list of document identifiers in r…