Xinggang Wang

Venues

Frequent coauthors

Papers

1. Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
   AAAI 2026 ·

   Zanwei Zhou

   DBLP profile ↗ORCID search ↗
2. Gait Recognition via Collaborating Discriminative and Generative Diffusion Models
   AAAI 2026 ·

   Haijun Xiong

   DBLP profile ↗ORCID search ↗
3. LENS: Learning to Segment Anything with Unified Reinforced Reasoning
   AAAI 2026 ·

   Lianghui Zhu

   DBLP profile ↗ORCID search ↗
4. MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning
   AAAI 2026 ·

   Wenrui Zhang

   DBLP profile ↗ORCID search ↗
5. Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids
   AAAI 2026 ·

   Ke Ma

   DBLP profile ↗ORCID search ↗
6. Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices
   AAAI 2026 ·

   Ya Zou

   DBLP profile ↗ORCID search ↗
7. WPIS: From In-the-Wild Web Images to Physics-Aware 3D Scene Graphs for Physical Reasoning
   WWW 2026 ·

   Ke Ma

   DBLP profile ↗ORCID search ↗
8. ControlAR: Controllable Image Generation with Autoregressive Models
   ICLR 2025 ·

   Zongming Li

   DBLP profile ↗ORCID search ↗
9. DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
   CVPR 2025 ·

   Lianghui Zhu

   DBLP profile ↗ORCID search ↗
10. DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
    CVPR 2025 ·

    Bencheng Liao

    DBLP profile ↗ORCID search ↗
11. Dynamic 2D Gaussians: Geometrically Accurate Radiance Fields for Dynamic Objects
    ACM MM 2025 ·

    Shuai Zhang

    DBLP profile ↗ORCID search ↗
12. GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images
    AAAI 2025 ·

    Ziyang Xu

    DBLP profile ↗ORCID search ↗
13. GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
    CVPR 2025 ·

    Haoyi Jiang

    DBLP profile ↗ORCID search ↗
14. Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
    NeurIPS 2025 ·

    Xiangyu Guo

    DBLP profile ↗ORCID search ↗
15. GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
    ICCV 2025 ·

    Rui Hu

    DBLP profile ↗ORCID search ↗
16. JudgeLM: Fine-tuned Large Language Models are Scalable Judges
    ICLR 2025 ·

    Lianghui Zhu

    DBLP profile ↗ORCID search ↗
17. MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling
    ICCV 2025 ·

    Yingyue Li

    DBLP profile ↗ORCID search ↗
18. Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation
    CVPR 2025 ·

    Yongkang Li

    DBLP profile ↗ORCID search ↗
19. RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
    NeurIPS 2025 ·

    Hao Gao

    DBLP profile ↗ORCID search ↗
20. Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
    CVPR 2025 ·

    Jingfeng Yao

    DBLP profile ↗ORCID search ↗
21. SuperCLIP: CLIP with Simple Classification Supervision
    NeurIPS 2025 ·

    Weiheng Zhao

    DBLP profile ↗ORCID search ↗
22. ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention
    AAAI 2025 ·

    Bencheng Liao

    DBLP profile ↗ORCID search ↗
23. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
    CVPR 2024 ·

    Guanjun Wu

    DBLP profile ↗ORCID search ↗
24. Cascade-Zero123: One Image to Highly Consistent 3D with Self-prompted Nearby Views
    ECCV 2024 ·

    Yabo Chen

    DBLP profile ↗ORCID search ↗
25. Causality-Inspired Discriminative Feature Learning in Triple Domains for Gait Recognition
    ECCV 2024 ·

    Haijun Xiong

    DBLP profile ↗ORCID search ↗
26. Co-Student: Collaborating Strong and Weak Students for Sparsely Annotated Object Detection
    ECCV 2024 ·

    Lianjun Wu

    DBLP profile ↗ORCID search ↗
27. FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
    NeurIPS 2024 ·

    Jingfeng Yao

    DBLP profile ↗ORCID search ↗
28. GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
    CVPR 2024 ·

    Taoran Yi

    DBLP profile ↗ORCID search ↗
29. Lane Graph as Path: Continuity-Preserving Path-Wise Modeling for Online Lane Graph Construction
    ECCV 2024 ·

    Bencheng Liao

    DBLP profile ↗ORCID search ↗
30. MoSt-DSA: Modeling Motion and Structural Interactions for Direct Multi-Frame Interpolation in DSA Images
    ECAI 2024 ·

    Ziyang Xu

    DBLP profile ↗ORCID search ↗
31. MobileInst: Video Instance Segmentation on the Mobile
    AAAI 2024 ·

    Renhong Zhang

    DBLP profile ↗ORCID search ↗
32. Occupancy as Set of Points
    ECCV 2024 ·

    Yiang Shi

    DBLP profile ↗ORCID search ↗
33. Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
    CVPR 2024 ·

    Haoyi Jiang

    DBLP profile ↗ORCID search ↗
34. Towards Dual Transparent Liquid Level Estimation in Biomedical Lab: Dataset, Methods and Practices
    ECCV 2024 ·

    Xiayu Wang

    DBLP profile ↗ORCID search ↗
35. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
    ICML 2024 ·

    Lianghui Zhu

    DBLP profile ↗ORCID search ↗
36. Visual Text Generation in the Wild
    ECCV 2024 ·

    Yuanzhi Zhu

    DBLP profile ↗ORCID search ↗
37. WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
    ACM MM 2024 ·

    Lianghui Zhu

    DBLP profile ↗ORCID search ↗
38. YOLO-World: Real-Time Open-Vocabulary Object Detection
    CVPR 2024 ·

    Tianheng Cheng

    DBLP profile ↗ORCID search ↗