CV

Download CV (PDF)

Education

• Ph.D in Computer Science, University of Technology Sydney, Australia, 2021. Supervised by Prof. Yi Yang.
• B.E. in Electronic and Information Engineering, University of Science and Technology of China, 2018.

Employment

• ZJU100 Young Professor, College of Artificial Intelligence, Zhejiang University, 2026–present.
• Research Fellow, Department of Biomedical Informatics (DBMI), Harvard Medical School, Harvard University, 2024–2026.
• Postdoctoral Researcher, CCAI, Zhejiang University, 2021–2024.
• Research Intern, Baidu Research, 2019–2021.

Publications

Replication in Visual Diffusion Models: A Survey and Outlook

Learning residue-level context for modeling protein-protein interactions

Photorealistic Text-to-3D Avatar Generation with Constraints for Decoupled Geometry and Appearance

Toward General-Purpose Video Reconstruction Through Synergy of Grid-Splicing Diffusion and Large Language Models

AI-powered medicinal chemistry and translational drug development

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Efficient training of large vision models via advanced automated progressive learning

SELongVLM: Empowering Long Video Language Models with Self-Corrective Clip Selection

Are Image-to-Video Models Good Zero-Shot Image Editors?

Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction

CLINES: Clinical LLM-based Information Extraction and Structuring Agent

A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studies

Insert Anything: Image Insertion via In-Context Editing in DiT

Test-Time Adaptation for Real-World Video Adverse Weather Restoration With Meta Batch Normalization

SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons

Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning

Exploiting EfficientSAM and Temporal Coherence for Audio-Visual Segmentation

3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering

Prompt-based multimodal representation learning for drug repurposing

MedSAM2: Segment Anything in 3D Medical Images and Videos

X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction

Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

The devil is in temporal token: High quality video reasoning segmentation

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

3DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis

Few-shot Incremental Learning via Foreground Aggregation and Knowledge Transfer for Audio-Visual Semantic Segmentation

GD-NeRF: Generative Detail Compensation for One-shot Generalizable Neural Radiance Fields

Show Me a Video: A Large-Scale Narrated Video Dataset for Coherent Story Illustration

Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data

MuscleParseNet: A Novel Framework for Parsing Muscles of Drosophila Larva in Light-Sheet Fluorescence Microscopy Images

IDPro: Flexible Interactive Video Object Segmentation by ID-Queried Concurrent Propagation

High Fidelity Makeup via 2D and 3D Identity Preservation Net

DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)

Scalable Video Object Segmentation with Identification Mechanism

Controllable 3D Face Generation with Conditional Style Code Diffusion

DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting

HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting

SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance

Human101: Training 100+ FPS Human Gaussians in 100s from 1 View

The First Visual Object Tracking Segmentation VOTS2023 Challenge Results

ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation

ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking

Shuffled Autoregression for Motion Interpolation

Collaborative Content-Dependent Modeling: A Return to the Roots of Salient Object Detection

CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation

AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation

Efficient Emotional Adaptation for Audio-driven Talking-Head Generation

TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering

JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery

Segment and Track Anything

Video Object Segmentation in Panoptic Wild Scenes

Pyramid Diffusion Models For Low-light Image Enhancement

Co-Learning Meets Stitch-Up for Noisy Multi-Label Visual Recognition

FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

ProD: Prompting-to-disentangle Domain Knowledge for Cross-domain Few-shot Image Classification

Decompose to Generalize: Species-Generalized Animal Pose Estimation

The Tenth Visual Object Tracking VOT2022 Challenge Results

V²L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval

Decoupling Features in Hierarchical Propagation for Video Object Segmentation

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

In-N-Out Generative Learning for Dense Unsupervised Video Segmentation

H²FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-domain Weakly Supervised Object Detection

Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation

Towards multi-object association from foreground-background integration

Associating Objects with Transformers for Video Object Segmentation

Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration

DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency

Memory aggregated cfbi+ for interactive video object segmentation

CFBI+: Collaborative video object segmentation by multi-scale foreground-background integration

Collaborative Video Object Segmentation by Foreground-Background Integration

Gated Channel Transformation for Visual Recognition

Going Deeper Into Embedding Learning for Video Object Segmentation

Dual Embedding Learning for Video Instance Segmentation

Very Long Natural Scenery Image Prediction by Outpainting

Service and leadership

• Invited Area Chair, ICLR 2027; Senior Program Committee Member, AAAI 2027; Area Chair, ECCV 2026; Outstanding Area Chair, CVPR 2026
• Workshop Organizer, Pixel-level Video Understanding in the Wild Challenge at CVPR 2023–2026