AI.info

Lu Wang

Explore Lu Wang on AI.info.

• Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
• Learning Ordinal Probabilistic Reward from Preferences
• G-KV: Decoding-Time KV Cache Eviction with Global Attention
• A Fast and Flat Federated Learning Method via Weighted Momentum and Sharpness-Aware Minimization
• Blur-Robust Detection via Feature Restoration: An End-to-End Framework for Prior-Guided Infrared UAV Target Detection
• GUI-360$^\circ$: A Comprehensive Dataset and Benchmark for Computer-Using Agents
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching
• Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
• LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?