Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper
•
2412.05271
•
Published
•
124
Zhaoyang Liu
zyliu
AI & ML interests
Video understanding, 3D Perception, Autonomous driving, Foundation models, AIGC
Recent Activity
authored
a paper
27 days ago
InternChat: Solving Vision-Centric Tasks by Interacting with Chatbots
Beyond Language
authored
a paper
27 days ago
Learning Human Motion Representations: A Unified Perspective
authored
a paper
27 days ago
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model
for Hundreds of Vision-Language Tasks
Organizations
