Haiyang Wang

Affiliations

Peking University

papers

530

total citations

papers (10)

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

CVPR 2023arXiv

183

citations

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

ICCV 2023arXiv

citations

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

NEURIPS 2025arXiv

citations

Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework

AAAI 2025arXiv

citations

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

ICLR 2025arXiv

citations

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

NEURIPS 2023arXiv

citations

MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds

NEURIPS 2022

citations

Haiyang Wang

Affiliations

papers (10)

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

RBGNet: Ray-Based Grouping for 3D Object Detection

Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds

papers (10)

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

RBGNet: Ray-Based Grouping for 3D Object Detection

Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds