Hao Liu

USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning Capabilities of LLMs as Urban Agents

CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control

Towards Multimodal Data-Driven Scientific Discovery Powered by LLM Agents

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Synergizing-Oriented Multi-Turn Reinforcement Learning

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction

MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

Language Model Empowered Spatio-Temporal Forecasting via Physics-Aware Reprogramming

JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework

Simplified Mamba with Disentangled Dependency Encoding for Long-Term Time Series Forecasting

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs

Privacy Preserving Generative Feature Transformation