Biography
Ling Yang is currently a final-year Ph.D. student at Peking University, advised by Bin Cui and Luxia Zhang. My research interests are Generative Modeling (Diffusion Models, LLMs) and AI for Science. I previously worked with Yang Song, Guohao Li, Shuicheng Yan, Ming-Hsuan Yang, Bernard Ghanem, Stefano Ermon, Mengdi Wang and Jure Leskovec. I serve as a program committee member or reviewer for international conferences and journals including SIGGRAPH, TPAMI, ICML, ICLR, NeurIPS, CVPR, KDD, AAAI. Feel free to contact me for potential collaborations or discussions.
Email | WeChat | Github | Google Scholar | Twitter
Research Summary
Diffusion Model
- Multimodal Generation: RPG, IterComp, VideoTetris, SemanticSDS, Trans4D, IPDreamer
- Diffusion Theory and Framework: ContextDiff, Consistency Flow Matching, Rectified Diffusion, ConPreDiff, SADM
- AI for Science: IPDiff, IRDiff, BindDM
Large Language Models
- Reasoning: Buffer of Thought (BoT), SuperCorrect
- Agent: Multi-Agent Collaborative Data Selection
- Data-centric Application: EditWorld
Representation Learning
- Graph-structured Data: DPGN, VQGraph, OEPG
- Suquential Data: BTSF, Cross Reconstruction Transformer
What's New
- I propose SupperCorrect, achieving new SOTA performance among all 7B models.
- I propose IterComp, leveraging iterative RLHF to achieve fast and realistic T2I generation.
- I propose SemanticSDS and Trans4D to enhance compositional generation in text-to-/3D/4D scenarios.
- Five papers about Diffusion Models and LLMs (Buffer of Thought, Spotlight) are accepted by NeurIPS 2024.
- One paper about diffusion-based video frame interpolation is accepted by ACM Multimedia 2024.
- I propose Consistency Flow Matching, converging 4.4x faster than Consistency Model and 1.7x faster than Rectified Flow while achieving better FID.
- I propose a new RAG-based LLM reasoning framework, Buffer of Thoughts, outperforming Tree of Thought.
- I release the project VideoTetris of first compositional text-to-video generation.
- Two papers about Diffusion Models and AI for Science are accepted by ICML 2024.
- One paper about general/molecular graph diffusion is accepted by TKDE 2024.
- One paper about improved training algorithm of Diffusion Transformers (DiT), DDPMs and Score SDEs is accepted by CVPR 2024.
- Release our SOTA LLM-controlled diffusion model, RPG-DiffusionMaster.
- Three papers about Diffusion Models, GNN, AI for Science are accepted by ICLR 2024.
- Our paper about protein-aware 3D molecular diffusion models is accepted by AAAI 2024.
- Our survey about Diffusion Models is accepted by ACM Computing Surveys 2023, collaborating with OpenAI.
- One paper about text-to-image diffusion is accepted by NeurIPS 2023.
- I publish a book about Diffusion Models.
- One paper is accepted by TNNLS 2023.
- One paper is accepted by TKDE 2023.
- Two papers are accepted as ICML 2022 Spotlight.
- One paper is accepted by CVPR 2020.
Selected Papers [Full List]
- Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs.
Ling Yang, Zhaochen Yu, Chenlin Meng, Minkai Xu, Stefano Ermon, Bin Cui
ICML 2024 paper | repo | tweet
- Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Ling Yang, Zhaochen Yu, Tianjun Zhang, Shiyi Cao, Minkai Xu, Wentao Zhang, Joseph E Gonzalez, Bin Cui
NeurIPS 2024 spotlight paper | repo | tweet
- IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
Xinchen Zhang*, Ling Yang*, Guohao Li, Yaqi Cai, Jiake Xie, Yong Tang, Yujiu Yang, Mengdi Wang, Bin Cui
paper | repo | tweet
- Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Ling Yang, Zixiang Zhang, Zhilong Zhang, Xingchao Liu, Minkai Xu, Wentao Zhang, Chenlin Meng, Stefano Ermon, Bin Cui
paper | repo | tweet - VideoTetris: Towards Compositional Text-to-Video Generation
Ye Tian*, Ling Yang*, Haotian Yang, Yuan Gao, Yufan Deng, Jingmin Chen, Xintao Wang, Zhaochen Yu, Xin Tao, Pengfei Wan, Di Zhang, Bin Cui
NeurIPS 2024 paper | repo | tweet
- Dpgn: Distribution propagation graph network for few-shot learning
Ling Yang, Liangliang Li, Zilun Zhang, Xinyu Zhou, Erjin Zhou, Yu Liu
CVPR 2020 paper | repo
Awards
- Selected for the distinguished student forum of VALSE 2024 (8 People in China).
- National Scholarship for Ph.D student (Top 1% in PKU), 2022.
- Exceptional Award for Academic Innovation for Ph.D student (Top 1% in PKU), 2022.
- First-class Academic Scholarship, 2018, 2019, 2020.