I'mTianheng Cheng, and have finished my Ph.D. career at theHUST Vision Lab of Huazhong University of Science and Technology.I’m now a researcher atByteDance Seed Team and working on cutting-edge large multimodal models and world models.

My lifelong research goal is to enable machines/robots tosee,understand, andlive like human beings.

Previous works/publications are listed atGoogle Scholar 📚.

Currently, I'm devoted to research aboutlarge multimodal models,foundational visual-language modeling, andimage generation. Before that, I mainly focused on fundamental tasks such asobject detection andinstance segmentation, as well as visual perception for autonomous driving.

Highlighted Works of those pinned works:

• ControlAR (ICLR 2025) explores controllable image generation with autoregressive models and empowers autoregressive models with arbitrary-resolution generation.
• MaskAdapter (CVPR 2025) integrates seamlessly into open-vocabulary segmentation methods based on mask pooling in a plug-and-play manner, delivering more accurate classification results.
• EVF-SAM (arXiv) empowers segment-anything (SAM, SAM-2) with the strong text-prompting ability. Try ourdemo on HuggingFace.
• OSP (ECCV 2024) explores sparse set of points to predict 3D semantic occupancy for autonomous vehicles, which is a brand new formulation!
• YOLO-World (CVPR 2024) for real-time open-vocabulary object detection;Symphonies (CVPR 2024) for camera-based 3D scene completion.
• SparseInst (CVPR 2022) aims for real-time instance segmentation with a simple fully convolutional framework!MobileInst (AAAI 2024) further explores temporal consistency and kernel reuse for efficient mobile video instance segmentation.
• BoxTeacher (CVPR 2023) bridges the gap between fully supervised and box-supervised instance segmentation. With ~1/10 annotation cost, BoxTeacher can achieve 93% performance versus fully supervised methods.

PinnedLoading

1. AILab-CVC/YOLO-WorldAILab-CVC/YOLO-WorldPublic

   [CVPR 2024] Real-Time Open-Vocabulary Object Detection

   Python 5.2k 499

2. hustvl/SparseInsthustvl/SparseInstPublic

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

   Python 600 73

3. hustvl/GKThustvl/GKTPublic

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

   Python 234 19

4. hustvl/Symphonieshustvl/SymphoniesPublic

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

   Python 177 5

5. hustvl/EVF-SAMhustvl/EVF-SAMPublic

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

   Python 375 18

6. hustvl/ControlARhustvl/ControlARPublic

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

   Python 207 6