Bingyi Kang

bykang's activity

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

authored 11 papers about 1 month ago

Improving Token-Based World Models with Parallel Observation Prediction

Paper • 2402.05643 • Published Feb 8, 2024 • 1

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

Paper • 2411.02359 • Published Nov 4, 2024 • 13

Classification Done Right for Vision-Language Pre-Training

Paper • 2411.03313 • Published Nov 5, 2024

Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models

Paper • 2412.14058 • Published Dec 18, 2024 • 1

Image Understanding Makes for A Good Tokenizer for Image Generation

Paper • 2411.04406 • Published Nov 7, 2024

$\text{M}^{\text{3}}$: A Modular World Model over Streams of Tokens

Paper • 2502.11537 • Published Feb 17

Improving and Benchmarking Offline Reinforcement Learning Algorithms

Paper • 2306.00972 • Published Jun 1, 2023

Deep Long-Tailed Learning: A Survey

Paper • 2110.04596 • Published Oct 9, 2021

Decoupling Representation and Classifier for Long-Tailed Recognition

Paper • 1910.09217 • Published Oct 21, 2019

Trace Anything: Representing Any Video in 4D via Trajectory Fields

Paper • 2510.13802 • Published Oct 15 • 30

Depth Anything 3: Recovering the Visual Space from Any Views

Paper • 2511.10647 • Published Nov 13 • 95

authored a paper 4 months ago

Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots

Paper • 2509.02530 • Published Sep 2 • 10

authored a paper 5 months ago

SpatialTrackerV2: 3D Point Tracking Made Easy

Paper • 2507.12462 • Published Jul 16 • 18

authored 2 papers 11 months ago

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Paper • 2501.12375 • Published Jan 21 • 23

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Paper • 2501.09781 • Published Jan 16 • 28

authored 3 papers about 1 year ago

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation

Paper • 2412.14015 • Published Dec 18, 2024 • 12

How Far is Video Generation from World Model: A Physical Law Perspective

Paper • 2411.02385 • Published Nov 4, 2024 • 34

Loong: Generating Minute-level Long Videos with Autoregressive Language Models

Paper • 2410.02757 • Published Oct 3, 2024 • 36

authored a paper over 1 year ago

Depth Anything V2

Paper • 2406.09414 • Published Jun 13, 2024 • 103

authored a paper almost 2 years ago

Bag of Tricks for Training Data Extraction from Language Models

Paper • 2302.04460 • Published Feb 9, 2023 • 2