4 citations · 8 across the 13 of their papers we have counts for
16 papers
Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning
Shiyu Miao, Yunlong Mao, Zirui Huang +5
Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface is a faithful derivative of…
DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation
Fan Liu, Hao Liu
Large Language Model (LLM) agents have shown promise for automating data-science workflows, yet their end-to-end performance depends critically on the agent harness that represents…
SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control
Bikang Pan, Fan Liu, Haotao Lu +2
World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future observations. However, conditioning future prediction only on the task prompt and ob…
SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents
Hang Ni, Weijia Zhang, Fan Liu +2
Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events. However, expert-centered warning wor…
DSWorld: A Data Science World Model for Efficient Autonomous Agents
Zherui Yang, Fan Liu, Hao Liu
Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computa…
ChartLens: A Dual-Branch Framework for Chart Data Correction and Factual Summary Refinement
Hao Liu, Ruping Cao, Kun Wang +4
In this report, we present our champion solution for the DataMFM Challenge Track 2: Chart Understanding. This track requires models to recover structured chart data and generate fa…
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
Zherui Yang, Fan Liu, Yansong Ning +1
Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their st…
Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition
Fan Liu, Jindong Han, Tengfei Lyu +5
Foundation models (FMs), such as GPT-4 and AlphaFold, are reshaping the landscape of scientific research. Beyond accelerating tasks such as hypothesis generation, experimental desi…
Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications
Jindong Han, Yansong Ning, Zirui Yuan +4
The long-standing vision of intelligent cities is to create efficient, livable, and sustainable urban environments using big data and artificial intelligence technologies. Recently…
MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem
Fan Liu, Zherui Yang, Cancheng Liu +3
Mathematical modeling is a cornerstone of scientific discovery and engineering practice, enabling the translation of real-world problems into formal systems across domains such as…
TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning
Hang Ni, Fan Liu, Xinyu Ma +5
Large language models (LLMs) have shown promise in automating travel planning, yet they often fall short in addressing nuanced spatiotemporal rationality. While existing benchmarks…
Bag of Tricks for Inference-time Computation of LLM Reasoning
Fan Liu, Wenshuo Chao, Naiqiang Tan +1
With the advancement of large language models (LLMs), solving complex reasoning tasks has gained increasing attention. Inference-time computation methods (e.g., Best-of-N, beam sea…
JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
Fan Liu, Yue Feng, Zhao Xu +4
Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM defenses remains a challenge, with current methods often lacking explainability and generaliz…
Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction
Ziyang Wu, Fan Liu, Jindong Han +2
As various types of crime continue to threaten public safety and economic development, predicting the occurrence of multiple types of crimes becomes increasingly vital for effectiv…
Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
Fan Liu, Zhao Xu, Hao Liu
Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak…
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
Zhao Xu, Fan Liu, Hao Liu
Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can…