Hongyang Li

compileme's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 4 months ago

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Paper • 2505.06111 • Published May 9 • 25

authored a paper 9 months ago

TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video

Paper • 2411.18671 • Published Nov 27, 2024 • 20

authored a paper over 1 year ago

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Paper • 2312.02949 • Published Dec 5, 2023 • 15

authored a paper almost 2 years ago

Visual In-Context Prompting

Paper • 2311.13601 • Published Nov 22, 2023 • 19