Dingkang Liang's picture

Dingkang Liang

dkliang

·

https://dk-liang.github.io/

dkliang

AI & ML interests

World Model, 3D Vision, Dense Object Analysis

Recent Activity

upvoted a paper about 6 hours ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

authored a paper 9 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

upvoted a paper 10 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

View all activity

Organizations

upvoted a paper about 6 hours ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published 3 days ago • 186

upvoted a paper 10 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published 13 days ago • 152

upvoted a paper 19 days ago

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Paper • 2603.19235 • Published 20 days ago • 94

upvoted 2 papers 22 days ago

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Paper • 2603.12262 • Published 27 days ago • 30

Towards Generalizable Robotic Manipulation in Dynamic Environments

Paper • 2603.15620 • Published 23 days ago • 3

upvoted 2 papers 4 months ago

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution

Paper • 2511.19430 • Published Nov 24, 2025 • 7

HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

Paper • 2501.14729 • Published Jan 24, 2025 • 3