Author

Xinggang Wang

Observed name: Wang, Xinggang

Institutions: ByteDance (China), Huazhong University of Science and Technology

Observed institutions: Huazhong University of Science and Technology Hospital, ByteDance (China), Huazhong University of Science and Technology

ORCID: 0000-0001-6732-7823

Observed ORCID: 0000-0001-6732-7823

OpenAlex ID: A5129663592

LENS: Learning to Segment Anything with Unified Reinforced Reasoning

2026 · Lianghui Zhu, Bin Ouyang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 3

Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

2026 · Ya Zou, Jingfeng Yao, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2

Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids

2026 · Ke Ma, Yizhou Fang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2

Mixture-of-Depths Attention

2026 · Zhu, Lianghui, Fang, Yuxin, et al. · arXiv (Cornell University) · 1

PDF

MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning

2026 · Wenrui Zhang, Xinggang Wang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

2025 · Yingyue Li, Bencheng Liao, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 1

PDF

Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation

2026 · Zhu, Yueting, Song, Yuehao, et al. · arXiv (Cornell University)

PDF

DreamWAM: Beyond RGB Future Prediction for World Action Models

2026 · Yuan, Shanglin, Zhao, Weiheng, et al. · arXiv (Cornell University)

PDF

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

2026 · Zhao, Weiheng, Jiang, Haoyi, et al. · arXiv (Cornell University)

PDF

EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass

2026 · Peng, Haomin, Li, Yongkang, et al. · arXiv (Cornell University)

PDF

MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model

2026 · Yuan, Shanglin, Zhao, Weiheng, et al. · arXiv (Cornell University)

PDF

Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning

2026 · Zhu, Yu, Li, Yongkang, et al. · arXiv (Cornell University)

PDF

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

2026 · Zanwei Zhou, Taoran Yi, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

PDF

TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation

2026 · Cao, Yiyang, Deng, Yunze, et al. · arXiv (Cornell University)

PDF

HBiP: Hierarchical Bimanual Manipulation via Visual Joint-actions as Intermediate Representation

2026 · Sixu Yan, Yuhan Li, et al. · SSRN Electronic Journal

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

2026 · Kangsheng Duan, Ziyang Xu, et al. · Lecture notes in computer science

PDF

DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis

2025 · Zhu, Yueting, Song, Yuehao, et al. · arXiv (Cornell University)

PDF

Visual Generation Tuning

2025 · Guo, Jiahao, Du, Sinan, et al. · arXiv (Cornell University)

PDF

Works count: 19

Citation count: 12

H-index: 2

I10-index: