Songyang Zhang

Affiliations

University of Rochester

papers

2,192

total citations

papers (20)

Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph Generation

CVPR 2021arXiv

249

citations

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

ICCV 2021arXiv

159

citations

SGTR: End-to-End Scene Graph Generation With Transformer

CVPR 2022arXiv

145

citations

The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

CVPR 2022arXiv

citations

Action Quality Assessment with Temporal Parsing Transformer

ECCV 2022arXiv

citations

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

CVPR 2024arXiv

citations

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

COLM 2025

citations

Improving Pixel-based MIM by Reducing Wasted Modeling Capability

ICCV 2023arXiv

citations

Dynamic Grained Encoder for Vision Transformers

NEURIPS 2021arXiv

citations

Learning Semantic Correspondence with Sparse Annotations

ECCV 2022arXiv

citations

RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer

CVPR 2023arXiv

citations

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

ECCV 2022arXiv

citations

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

AAAI 2025arXiv

citations

Rethinking Verification for LLM Code Generation: From Generation to Testing

NEURIPS 2025arXiv

citations

LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation

ICCV 2025arXiv

citations

FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data

ICML 2024arXiv

citations

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game

AAAI 2025arXiv

citations

Songyang Zhang

Affiliations

papers (20)

Expanding Language-Image Pretrained Models for General Video Recognition

Part-aware Prototype Network for Few-shot Semantic Segmentation

Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition

Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph Generation

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

SGTR: End-to-End Scene Graph Generation With Transformer

The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Action Quality Assessment with Temporal Parsing Transformer

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Improving Pixel-based MIM by Reducing Wasted Modeling Capability

Dynamic Grained Encoder for Vision Transformers

Learning Semantic Correspondence with Sparse Annotations

RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

Rethinking Verification for LLM Code Generation: From Generation to Testing

LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation

FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game

papers (20)

Expanding Language-Image Pretrained Models for General Video Recognition

Part-aware Prototype Network for Few-shot Semantic Segmentation

Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition

Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph Generation

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

SGTR: End-to-End Scene Graph Generation With Transformer

The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Action Quality Assessment with Temporal Parsing Transformer

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Improving Pixel-based MIM by Reducing Wasted Modeling Capability

Dynamic Grained Encoder for Vision Transformers

Learning Semantic Correspondence with Sparse Annotations

RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

Rethinking Verification for LLM Code Generation: From Generation to Testing

LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation

FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game