AI.info

Jian Li

Explore Jian Li on AI.info.

• ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding
• RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
• CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
• Gaussian Belief Propagation Network for Depth Completion
• Deep Incomplete Multi-View Clustering via Hierarchical Imputation and Alignment
• FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
• Disco-RAG: Discourse-Aware Retrieval-Augmented Generation
• Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization
• L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention
• RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving
• Gentle Manipulation Policy Learning via Demonstrations from VLM Planned Atomic Skills