Bingyi Kang

papers

2,348

total citations

papers (13)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

CVPR 2024arXiv

1,479

citations

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

CVPR 2020arXiv

293

citations

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

NEURIPS 2023arXiv

citations

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation

CVPR 2025arXiv

citations

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

CVPR 2025arXiv

citations

Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL

NEURIPS 2023arXiv

citations

Improving Token-Based World Models with Parallel Observation Prediction

ICML 2024arXiv

citations

Mutual Information Regularized Offline Reinforcement Learning

NEURIPS 2023arXiv

citations

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

ECCV 2020

citations

SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion

ICCV 2025

citations

Bingyi Kang

papers (13)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

Improving Generalization in Reinforcement Learning with Mixture Regularization

Efficient Diffusion Policies For Offline Reinforcement Learning

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

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL

Improving Token-Based World Models with Parallel Observation Prediction

Mutual Information Regularized Offline Reinforcement Learning

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion

papers (13)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

Improving Generalization in Reinforcement Learning with Mixture Regularization

Efficient Diffusion Policies For Offline Reinforcement Learning

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

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL

Improving Token-Based World Models with Parallel Observation Prediction

Mutual Information Regularized Offline Reinforcement Learning

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion