370 citations · 1.3k across the 77 of their papers we have counts for
77 papers
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…
Unsupervised Skill Discovery for Agentic Data Analysis
Zhisong Qiu, Kangqi Song, Shengwei Tang +4
Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However,…
SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research
Shuofei Qiao, Yunxiang Wei, Busheng Zhang +16
Artificial intelligence is rapidly entering the core workflows of scientific research. Yet reliable scientific reasoning requires access to accumulated scientific knowledge with su…
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…
KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks
Zekun Xi, Yichen Nie, Ziyan Jiang +5
Despite the rapid advancement of generative agents, their deployment in real-world industry scenarios often encounters significant challenges due to a lack of domain-specific knowl…
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Chenxi Wang, Zhuoyun Yu, Xin Xie +8
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, r…
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Ziwen Xu, Kewei Xu, Haoming Xu +8
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Wi…
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,…
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…
Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
Xiang Chen, Yixin Ou, Quan Feng +8
The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and…
InnoGym: Benchmarking the Innovation Potential of AI Agents
Jintian Zhang, Kewei Xu, Jingsheng Zheng +10
LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness,…
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…
OceanGym: A Benchmark Environment for Underwater Embodied Agents
Yida Xue, Mingjun Mao, Xiangyuan Ru +9
We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike t…
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
Mengru Wang, Ziwen Xu, Shengyu Mao +4
Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model b…
ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
Kangwei Liu, Siyuan Cheng, Bozhong Tian +7
Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the ov…
ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
Haoming Xu, Shuxun Wang, Yanqiu Zhao +6
This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models. This task aims to selectively erase sensitive kn…
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…
ReLearn: Unlearning via Learning for Large Language Models
Haoming Xu, Ningyuan Zhao, Liming Yang +7
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent token…
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…
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Chenxi Wang, Xiang Chen, Ningyu Zhang +4
Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena, but the underlying reasons remain poorly understood. In this paper, we present an empirical ana…
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…