Xinlei He

Work Zones challenge VLM Trajectory Planning: Toward Mitigation and Robust Autonomous Driving

JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models

CodeInsightBench: A Benchmark for Advanced Code Understanding and Comparison in Large Language Models

Inference-time Unlearning via Adaptive Output Regulation

Prediction Inconsistency Helps Generalizable Detection of Adversarial Examples

Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond

FacLens: Transferable Probe for Foreseeing Non-Factuality in Large Language Models

Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks