370 citations · 587 across the 44 of their papers we have counts for
45 papers
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Mengru Wang, Junfeng Fang, Shuofei Qiao +17
AI models are increasingly used in scientific discovery and human decision-making. Yet how AI models work and what risks they pose remain poorly understood. As AI development becom…
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Yijun Chen, Yaqi Zheng, Yanya Li +11
Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as iso…
PRISM Edit: One Vector for All Temporal Answers
Chen Huang, Qi Zheng, Ruiqin Zheng +2
Model editing keeps large language models (LLMs) up to date without retraining, but temporal facts expose a limitation of the prevailing locate-and-edit paradigm: an update is not…
Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models
Huafu Li, Guo Chen, Jia Xia +5
Visual information extraction (VIE) from visually rich documents remains challenging due to high layout variability and real-world impairments. Existing methods typically rely on s…
A theoretical model for task routing in mixture-of-expert transformers
Vinoth Nandakumar, Yongli Xiang, Yunzhi Yao +2
Mixture-of-experts (MoE) layers enable the scaling of transformer models while keeping the inference compute fixed. While task-expert specialization has been observed in empirical…
TokenPilot: Cache-Efficient Context Management for LLM Agents
Buqiang Xu, Zirui Xue, Dianmou Chen +12
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize…
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Haoming Xu, Weihong Xu, Zongrui Li +6
Long-horizon interactions require language models to manage accumulating information: when to update their state, when to preserve their state, and what to ignore. We study this ch…
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
Xinle Deng, Ruobin Zhong, Hujin Peng +15
Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dyn…
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
Buqiang Xu, Yijun Chen, Jizhan Fang +5
Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answe…
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
Ziheng Chen, Jiali Cheng, Zezhong Fan +4
Recent advances in large language models (LLMs) have opened new opportunities for recommender systems by enabling rich semantic understanding and reasoning about user interests and…
From Data to Behavior: Predicting Unintended Model Behaviors Before Training
Mengru Wang, Zhenqian Xu, Junfeng Fang +4
Large Language Models (LLMs) can acquire unintended biases from seemingly benign training data even without explicit cues or malicious content. Existing methods struggle to detect…
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Ziwen Xu, Chenyan Wu, Hengyu Sun +9
Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation,…
Aligning Agentic World Models via Knowledgeable Experience Learning
Baochang Ren, Yunzhi Yao, Rui Sun +3
Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of th…
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Haoming Xu, Ningyuan Zhao, Yunzhi Yao +7
As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under…
How Do Large Language Models Learn Concepts During Continual Pre-Training?
Barry Menglong Yao, Sha Li, Yunzhi Yao +4
Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large lan…
LightMem: Lightweight and Efficient Memory-Augmented Generation
Jizhan Fang, Xinle Deng, Haoming Xu +9
Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory…
Energy-Regularized Sequential Model Editing on Hyperspheres
Qingyuan Liu, Jia-Chen Gu, Yunzhi Yao +2
Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequen…
ReCode: Updating Code API Knowledge with Reinforcement Learning
Haoze Wu, Yunzhi Yao, Wenhao Yu +1
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemmi…
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Mengru Wang, Xingyu Chen, Yue Wang +12
Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structur…
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
Ziwen Xu, Shuxun Wang, Kewei Xu +7
In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide ra…
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
Yunzhi Yao, Jizhan Fang, Jia-Chen Gu +4
Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they ofte…
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Yixin Ou, Yunzhi Yao, Ningyu Zhang +5
Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly ho…
Exploring Model Kinship for Merging Large Language Models
Yedi Hu, Yunzhi Yao, Ningyu Zhang +2
Model merging has emerged as a key technique for enhancing the capabilities and efficiency of Large Language Models (LLMs). The open-source community has driven model evolution by…
OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Ningyu Zhang, Zekun Xi, Yujie Luo +11
Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs…