AI.info

Lei Li

Explore Lei Li on AI.info.

• Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies
• TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
• Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment
• PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
• Medal S: Spatio-Textual Prompt Model for Medical Segmentation
• JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
• Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation