Bingyi Kang

Bingyi Kang on Hugging Face Daily Papers: 14 papers, 5 in the top 3 of their day, 507 upvotes.

1. Depth Anything 3: Recovering the Visual Space from Any Views 77 upvotes, #2 of 2025-11-14
2. Trace Anything: Representing Any Video in 4D via Trajectory Fields 30 upvotes, #7 of 2025-10-16
3. Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots 8 upvotes, #8 of 2025-09-04
4. SpatialTrackerV2: 3D Point Tracking Made Easy 13 upvotes, #10 of 2025-07-17
5. Video Depth Anything: Consistent Depth Estimation for Super-Long Videos 21 upvotes, #11 of 2025-01-22
6. VideoWorld: Exploring Knowledge Learning from Unlabeled Videos 24 upvotes, #2 of 2025-01-21
7. Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation 12 upvotes, #12 of 2024-12-19
8. DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution 12 upvotes, #4 of 2024-11-06
9. How Far is Video Generation from World Model: A Physical Law Perspective 29 upvotes, #4 of 2024-11-05
10. Loong: Generating Minute-level Long Videos with Autoregressive Language Models 35 upvotes, #4 of 2024-10-04
11. Depth Anything V2 83 upvotes, #1 of 2024-06-14
12. Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data 64 upvotes, #1 of 2024-01-22
13. BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs 29 upvotes, #3 of 2023-07-18
14. Efficient Diffusion Policies for Offline Reinforcement Learning 2 upvotes, #5 of 2023-06-01

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.