李泽健
平台“百人计划”研究员 · 博士生导师研究智能设计，关注图像生成技术在人机协同创作中的应用。
任职于浙江大学软件学院，2019年获浙江大学计算机科学与技术博士学位。
研究方向包括生成模型、智能设计及人工智能辅助文化遗产保护，学术成果发表于CHI、ICLR、CVPR、AAAI、ICCV等国际会议。
相关成果曾获世界人工智能大会最高奖SAIL奖、中国“好设计”创意奖，并参展“双创”周、中国国际工业博览会等。代表作品包括“墨染”系列国画创作系统、《运河·生长·万象》系列作品及人工智能发展简史图谱。
曾主持国家自然科学基金青年项目，并作为核心骨干参与科技部“新一代人工智能”重大项目、教育部人工智能算法规划研究项目和浙江省重点研发计划等。
项目与作品
- MoWorld 参与
- 运河·生长·万象 创作团队
- 墨染 参与
- 人工智能发展简史图谱 视觉设计
- PoemPalette 团队成员
- 3DInkGen 团队成员
- InkRenew 团队成员
- Ink Restorer 团队成员
- RealtimeGen 团队成员
- FusionProtor 团队成员
- 神笔 团队成员
- CharacterCritique 团队成员
- Artist 1.0 · 印象江南 项目参与
研究论文 · 43篇
2026CHI
PoemPalette: Facilitating Poetry Creative Exploration and Foundational Understanding through the Ideorealm Alignment of Paintings and Poems
2026ACL
ThinkPersona: Thinking with Persona Graphs for Faithful Individualized Role-Playing
2026AAAI
Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
2026ACM MM
SEPO: Self-Evolving Preference Optimization for Diffusion Alignment via Dynamic Rule Refinement
2026IJCV
SCoRE: Standardized Human Evaluation Provides a Reliable Measure for Semantic Consistency of Text-to-Image Generation
2026CVPR
Circular-DPO: Aligning Multi-Stage 3D Generative Models via Preference Feedback Loop
2026CHI
Does Sycophancy Change Decisions? Effect of LLM Sycophancy on AI-Assisted Decision-Making
2026CHI EA · 扩展摘要
NarrAid: Supporting Storytelling of People with Aphasia via Generative Visual Scene Displays
2026CHI
3DInkGen: Extending Traditional Ink-Painting Artistry with Generative 3D Creation for Novices
2026HSSC
From Traditional Craft to Digital Restoration: An Intelligent Rebirth of Ancient Chinese Painting Restoration Technique
2026ECCV
InstaPano: Zero-shot Instance Layout Controlled Panorama Generation Via Global Attention Fusion
2026ICML
Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models
2026arXiv · 预印本
Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes
2025ICLR
Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation
2025CHI
Ink Restorer: Virtual Restoration of Ancient Chinese Paintings Inheriting Traditional Restoration Processes
2025ACM MM
ObjCtrl: Object-based Control Relaxation for Conditional Text-to-Image Generation
2025IEEE TII
Img2CAD: Conditioned 3-D CAD Model Generation From Single Image With Structured Visual Geometry
2025arXiv · 预印本
Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches
2025arXiv · 预印本
Syllables to Scenes: Literary-Guided Free-Viewpoint 3D Scene Synthesis from Japanese Haiku
2025CHI
CharacterCritique: Supporting Children’s Development of Critical Thinking through Multi-Agent Interaction in Story Reading
2025IJHCI
RealtimeGen: An Intervenable AI Image Generation System for Commercial Digital Art Asset Creators
2025ICCV
Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion
2025ACM MM
Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
2025FITEE
Image Generation Evaluation: A Comprehensive Survey of Human and Automatic Evaluations
2025CHI
FusionProtor: A Mixed-Prototype Tool for Component-level Physical-to-Virtual 3D Transition and Simulation
2025CAAD FuturesBest Paper Award
Automating 3D Building Layouts with Graph Neural Networks for Architectural Space Layout Modeling
2024FITEE
Deep3DSketch-im: rapid high-fidelity AI 3D model generation by single freehand sketches
2024IEEE TMM
Reality3DSketch: Rapid 3D Modeling of Objects From Single Freehand Sketches
2024AAAI
Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
2024CVPR
Rapid 3D Model Generation with Intuitive 3D Input
2024arXiv · 预印本
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations
2023IJCAI
Learning Object Consistency and Interaction in Image Generation from Scene Graphs
2023FITEE
UI layers merger: merging UI layers via visual learning and boundary prior
2023AAAI
Preserving Structural Consistency in Arbitrary Artist and Artwork Style Transfer
2023ECML PKDD 2022 · 论文集发表于 2023
Recognizing Cognitive Load by a Hybrid Spatio-Temporal Causal Model from Multivariate Physiological Data
2023ICCV Workshops · Workshop论文
SAM-Adapter: Adapting Segment Anything in Underperformed Scenes
2022Neurocomputing
USIS: A unified semantic image synthesis model trained on a single or multiple samples
2022CVPR
Few-Shot Incremental Learning for Label-to-Image Translation
2021ICCV
Image Synthesis From Layout With Locality-Aware Mask Adaption
2020AAAI
FET-GAN: Font and Effect Transfer via K-shot Adaptive Instance Normalization
2019FITEE
A review of design intelligence: progress, problems, and challenges
2019AAAI
Learning Disentangled Representation with Pairwise Independence
2018IJCAI
Unsupervised Disentangled Representation Learning with Analogical Relations
学术荣誉
CAAD Futures 2025 Best Paper Award