Ruiping Wang

Full Professor@Institute of Computing Technology, Chinese Academy of Sciences·中国·OpenReview

研究方向

object recognition · object detection · scene understanding · image retrieval · video retrieval · visual question answering · 3D vision · manifold learning · metric learning · kernel learning · hash learning · face recognition · facial image analysis

Ruiping Wang

Scaling Laws for Fully Sparsely-Activated Large Language Models

MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models

Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation

R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner