hustvl

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

You Only Look Once for Panopitic Driving Perception.（MIR2022）

[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

[CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

[ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

[NeurIPS 2021] You Only Look at One Sequence

[CVPR 2024] GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models

[CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation

PixelHacker: Image Inpainting with Structural and Semantic Consistency

[Image and Vision Computing (Vol.147 Jul. '24)] Interactive Natural Image Matting with Segment Anything Models

[Information Fusion (Vol.103, Mar. '24)] Boosting Image Matting with Pretrained Plain Vision Transformers

[ECCV 2026] Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

[IJCV 2026] Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"

[ICCV 2021] Instances as Queries

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022

DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving

TiNeuVox: Fast Dynamic Radiance Fields with Time-Aware Neural Voxels (SIGGRAPH Asia 2022)

[ICCV 2023] You Only Look at One Partial Sequence

A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type

Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

[ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models

[NeurIPS 2025 & TPAMI ] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".

Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral

GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality

[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

[CVPR 2024] Symphonies (Scene-from-Insts): Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

[ECCV 2020] Boundary-preserving Mask R-CNN

[CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

[ACM MM 2025] Dynamic 2D Gaussians: Geometrically Accurate Radiance Fields for Dynamic Objects

Hierarchical Aggregation for 3D Instance Segmentation (ICCV 2021)

Official PyTorch implementation of SparseTrack

[ECCV 2026] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

[ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

[TIP, IEEE Transactions on Image Processing] WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

[AAAI 2026] Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

[AAAI 2026 Oral] LENS: Learning to Segment Anything with Unified Reinforced Reasoning

[CVPR 2025] Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"

[ECCV 2026] OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

[NeurIPS 2026] InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

[AAAI 2025] Linear-complexity Visual Sequence Learning with Gated Linear Attention

[ArXiv 2025] MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices

[Nature Portfolio, npj DigitalMed] EVA-X: A foundation model for general chest X-ray analysis with self-supervised learning

The first decoder-only multimodal state space model

Visual Generation Tuning

[ECCV 2024] Occupancy as Set of Points

Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”

[ICCV 2021] Crossover Learning for Fast Online Video Instance Segmentation

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

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens (CVPR 2022)

[CVPR 2023] Exploring High-Quality Pseudo Masks for Weakly Supervised Instance Segmentation

[IJCV 2025] MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning

[ICCV 2025] GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

GNeuVox: Generalizable Neural Voxels for Fast Human Radiance Fields

Official code of "ViTGaze: Gaze Following with Interaction Features in Vision Transformers"

[CVPR 2023] PD-Quant: Post-Training Quantization Based on Prediction Difference Metric

[ACM MM 2024] WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception, CVPR 2022.

PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification

Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning