AI.info

Xiang Wang

Explore Xiang Wang on AI.info.

• HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
• GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models
• MAR: Efficient Large Language Models via Module-aware Architecture Refinement
• DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
• OceanForecastBench: A Benchmark Dataset for Data-Driven Global Ocean Forecasting
• Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
• Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
• Teaching Language Models to Reason with Tools