AI.info

Kai Han

Explore Kai Han on AI.info.

• JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing
• Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
• GSPN-2: Efficient Parallel Sequence Modeling
• Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation
• VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
• PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
• PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models
• Mitigating Coordinate Prediction Bias from Positional Encoding Failures
• SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery