Ling Yang — Princeton University

Ling Yang 杨灵

Postdoctoral Scholar · Princeton University

I am currently a Postdoctoral Scholar in the Department of ECE at Princeton University, co-affiliated with Princeton AI Lab, fortunately working with Prof. Mengdi Wang. Prior to this, I served as a Senior Research Assistant at Princeton University from January to July 2025. I received my Ph.D. degree from Peking University in July 2025, jointly supervised by Prof. Bin Cui and Prof. Luxia Zhang. During my doctoral studies, I was selected for the ByteDance Top Seed Talent Program.

My research builds toward Super Generative Intelligence — see Research Summary for a full overview of ongoing work across generative model foundations (large language models, reinforcement learning, and diffusion models), multimodal applications, and intelligent agent systems. I lead the Gen-Verse team at Princeton. Our open-source projects have accumulated 10,000+ GitHub Stars and 200,000+ HuggingFace Downloads.

2 papers about multimodal reinforcement learning are accepted by CVPR 2026.

4 papers about LLMs and Diffusion Language Models are accepted by ICLR 2026, including TraceRL & TraDo, OmniVerifier Oral, Top 1%, MMaDA-Parallel and UltraViCo.

We release a series of works about efficient agent reasoning and agentic training: LatentMAS, RLAnything, and GenEnv.

Our AutoTool won Best Paper Award at ICCV 2025 Workshop on MMRAgI.

Invited to give a talk at ICCV 2025 Workshop on Multi-Modal Reasoning for Agentic Intelligence.

5 papers about LLMs and Multimodal LLMs are accepted by NeurIPS 2025, including MMaDA, CURE & ReasonFlux-Coder Spotlight, Top 3%, ReasonFlux-PRM, Transformer-Copilot Spotlight, Top 3% and HermesFlow.

3 papers about LLMs and Agents are accepted by EMNLP 2025, including EmoAgent Oral, Top 1% and TreeBoN.

2 papers about diffusion are accepted by ACM MM 2025, including Inversion-DPO and EditWorld.

I was selected as a finalist for the 2025 WAIC Yunfan Award.

Invited to participate in a roundtable forum at WAIC 2025, hosted by Prof. Dahua Lin.

2 papers about agent and diffusion are accepted by ICCV 2025, including ScoreLiDAR Oral, Top 1% and Paper2Video Agent.

1 paper about LLMs is accepted by ACL 2025, including Multi-Actor Collaboration.

I was invited as an Area Chair at NeurIPS 2025.

6 papers about LLMs and Diffusion Models are accepted by ICLR 2025, including SuperCorrect, Rectified Diffusion, IterComp and IPDreamer.

Invited to give a talk at Princeton AI Lab, hosted by Prof. Mengdi Wang.

5 papers about Diffusion Models and LLMs are accepted by NeurIPS 2024, including Buffer of Thoughts Spotlight, Top 3%.

2 papers about Diffusion Models and AI for Science are accepted by ICML 2024.

1 paper about general/molecular graph diffusion is accepted by TKDE 2024.

1 paper about improved training algorithm of DiT, DDPMs and Score SDEs is accepted by CVPR 2024.

3 papers about Diffusion Models, GNN, AI for Science are accepted by ICLR 2024.

1 paper about molecular diffusion models is accepted by AAAI 2024.

1 paper about diffusion model survey collaborating with OpenAI is accepted by ACM Computing Surveys.

1 paper about diffusion models is accepted by NeurIPS 2023.

I publish a book about Diffusion Models.

1 paper is accepted by TNNLS 2023.

1 paper is accepted by TKDE 2023.

2 papers are accepted as ICML 2022 Spotlight, Top 3%.

1 paper is accepted by CVPR 2020.

Open Positions

Research Summary

Language Model Innovations

Large-Scale Reinforcement Learning

Intelligent Agent Systems

Diffusion Model Foundations

Multimodal Content Generation

AI for Scientific Discovery

📖 Book Publication

What's New

Selected Publications

RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System

Latent Collaboration in Multi-Agent Systems

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

MMaDA: Multimodal Large Diffusion Language Models

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning (ReasonFlux-Coder)

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

Generative Universal Verifier as Multimodal Meta-Reasoner

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing

Structure-Guided Adversarial Training of Diffusion Models

Improving Diffusion-Based Image Synthesis with Context Prediction

Diffusion Models: A Comprehensive Survey of Methods and Applications

VideoTetris: Towards Compositional Text-to-Video Generation

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

DPGN: Distribution Propagation Graph Network for Few-Shot Learning

Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety

Invited Talks

Honors & Awards

2025 WAIC Yunfan Award Finalist

Outstanding Graduate

KAUST Rising Stars in AI Symposium

VALSE Distinguished Student Forum

Outstanding Author

National Scholarship for Ph.D. Students

Exceptional Award for Academic Innovation

Academic Services

Area Chair

Program Committee / Reviewer

Journal Reviewer