AI.info

Wei Li

Explore Wei Li on AI.info.

• EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue
• Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
• Continual GUI Agents
• Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
• Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
• Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
• InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck
• Light-X: Generative 4D Video Rendering with Camera and Illumination Control
• LAOF: Robust Latent Action Learning with Optical Flow Constraints
• SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
• Real Garment Benchmark (RGBench): A Comprehensive Benchmark for Robotic Garment Manipulation featuring a High-Fidelity Scalable Simulator
• UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis