Lijun Li

GhostEI-Bench: Do Mobile Agent Resilience to Environmental Injection in Dynamic On-Device Environments?

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models

Unintended Harmful Knowledge Elicitation Issue in Large Reasoning Models and a RL Solution

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory

STaR-Attack: A Spatio-Temporal and Narrative Reasoning Attack Framework for Unified Multimodal Understanding and Generation Models

ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning

Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning

WorldSimBench: Towards Video Generation Models as World Simulators

WorldSimBench: Towards Video Generation Models as World Simulators

Benchmarking Ethics in Text-to-Image Models: A Holistic Dataset and Evaluator for Fairness, Toxicity, and Privacy