2.1k citations · 2.1k across the 31 of their papers we have counts for
33 papers
What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
Yuxuan Gu, Kequan Niu, Xiaocheng Feng +3
Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introduce desired reasoning strategie…
CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs
Yangfan Ye, Xiaocheng Feng, Jialong Tang +5
Existing research largely reduces cultural intelligence in LLMs to a knowledge-level problem, overlooking whether models can effectively utilize their acquired knowledge in realist…
CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
Qiming Li, Zekai Ye, Xiaocheng Feng +9
Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, l…
Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation
Zekun Yuan, Yangfan Ye, Xiaocheng Feng +5
Large language models (LLMs) have achieved strong performance in general machine translation, yet their ability in culture-aware scenarios remains poorly understood. To bridge this…
SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution
Xiachong Feng, Yi Jiang, Xiaocheng Feng +9
Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learni…
Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play
Xiachong Feng, Deyi Yin, Xiaocheng Feng +9
Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adapti…
Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models
Zekai Ye, Qiming Li, Xiaocheng Feng +6
While Reinforcement Learning from Verifiable Rewards (RLVR) has advanced reasoning in Large Vision-Language Models (LVLMs), prevailing frameworks suffer from a foundational methodo…
Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?
Yuxuan Gu, Lunjun Liu, Xiaocheng Feng +4
An essential problem in artificial intelligence is whether LLMs can simulate human cognition or merely imitate surface-level behaviors, while existing datasets suffer from either s…
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Lei Huang, Xiang Cheng, Chenxiao Zhao +6
Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorit…
PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
Xiachong Feng, Liang Zhao, Weihong Zhong +5
Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human…
Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management
Weitao Ma, Xiaocheng Feng, Lei Huang +7
Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specia…
WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning
Xinmiao Yu, Liwen Zhang, Xiaocheng Feng +4
Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, pl…
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents
Ruihan Chen, Qiming Li, Xiaocheng Feng +9
Large Vision-Language Models (LVLMs) have shown strong potential as multilingual Graphical User Interface (GUI) agents, as evidenced by existing GUI benchmarks. However, these benc…
Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering
Kun Zhu, Lizi Liao, Yuxuan Gu +3
The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised cl…
FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging
Zijian Li, Xiaocheng Feng, Huixin Liu +3
With the development of large language models, fine-tuning has emerged as an effective method to enhance performance in specific scenarios by injecting domain-specific knowledge. I…
From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems
Zekun Zhou, Xiaocheng Feng, Lei Huang +11
Research is a fundamental process driving the advancement of human civilization, yet it demands substantial time and effort from researchers. In recent years, the rapid development…
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
Lei Huang, Xiaocheng Feng, Weitao Ma +9
Ensuring contextual faithfulness in retrieval-augmented large language models (LLMs) is crucial for building trustworthy information-seeking systems, particularly in long-form ques…
Length Controlled Generation for Black-box LLMs
Yuxuan Gu, Wenjie Wang, Xiaocheng Feng +5
Large language models (LLMs) have demonstrated impressive instruction following capabilities, while still struggling to accurately manage the length of the generated text, which is…
Discrete Modeling via Boundary Conditional Diffusion Processes
Yuxuan Gu, Xiaocheng Feng, Lei Huang +5
We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the…
Advancing Large Language Model Attribution through Self-Improving
Lei Huang, Xiaocheng Feng, Weitao Ma +7
Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. Howe…
GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization
Yangfan Ye, Xiachong Feng, Xiaocheng Feng +6
News summarization in today's global scene can be daunting with its flood of multilingual content and varied viewpoints from different sources. However, current studies often negle…
Extending Context Window of Large Language Models from a Distributional Perspective
Yingsheng Wu, Yuxuan Gu, Xiaocheng Feng +5
Scaling the rotary position embedding (RoPE) has become a common method for extending the context window of RoPE-based large language models (LLMs). However, existing scaling metho…
Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
Weihong Zhong, Xiaocheng Feng, Liang Zhao +6
Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is tha…
An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation
Kun Zhu, Xiaocheng Feng, Xiyuan Du +7
Retrieval-augmented generation integrates the capabilities of large language models with relevant information retrieved from an extensive corpus, yet encounters challenges when con…