Bingyi Kang
- Papers
- 18
Cite
Notes
Only stored in your browser.
Authored papers
18VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
arXiv 2026
Uncovering Untapped Potential in Sample-Efficient World Model Agents
arXiv 2025
SpatialTrackerV2: 3D Point Tracking Made Easy
spatialtrackerv2-3d-point-tracking-made-easy
Depth Anything 3: Recovering the Visual Space from Any Views
arXiv 2025
Trace Anything: Representing Any Video in 4D via Trajectory Fields
arXiv 2025
Depth Anything V2
arXiv 2024
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
CVPR 2025 1
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
CVPR 2024 1
Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models
arXiv 2024
Classification Done Right for Vision-Language Pre-Training
arXiv 2024
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
arXiv 2024
Image Understanding Makes for A Good Tokenizer for Image Generation
arXiv 2024
Improving Token-Based World Models with Parallel Observation Prediction
arXiv 2024
Efficient Diffusion Policies for Offline Reinforcement Learning
efficient-diffusion-policies-for-offline
Bag of Tricks for Training Data Extraction from Language Models
arXiv 2023
Improving and Benchmarking Offline Reinforcement Learning Algorithms
arXiv 2023
Deep Long-Tailed Learning: A Survey
arXiv 2021
Decoupling Representation and Classifier for Long-Tailed Recognition
ICLR 2020 1
Affiliations
Frequent co-authors
10from 18 papers