Yuwen Xiong

17

Papers

127

Total Citations

Papers (17)

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

Deep Feature Flow for Video Recognition

Deep Rigid Instance Scene Flow

UPSNet: A Unified Panoptic Segmentation Network

PolyTransform: Deep Polygon Transformer for Instance Segmentation

Learning Compact Representations for LiDAR Completion and Generation

Deformable Convolutional Networks

DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation

Self-Supervised Representation Learning From Flow Equivariance

Weakly-supervised 3D Shape Completion in the Wild

Rethinking Closed-Loop Training for Autonomous Driving

Towards Unsupervised Object Detection From LiDAR Point Clouds

LangBridge: Interpreting Image as a Combination of Language Embeddings

LoCo: Local Contrastive Representation Learning

Reviving and Improving Recurrent Back-Propagation