Yuanlin Duan(段源林)Ph.D. StudentDepartment of Computer Science Rutgers University, New Brunswick Email: yuanlin.duan@rutgers.edu
|
|
Bio
I am a fourth-year PhD student in the Department of CS at Rutgers University, advised by Professor
He Zhu. Prior to Rutgers, I got my B.E. degree in Artificial Intelligence
at UESTC. In summer 2026 I was a Machine Learning Scientist Intern at
TikTok in San Jose, CA.
Research Interests
My research asks a single question: how can an agent learn a task quickly when the reward is sparse? In a sparse-reward environment the agent sees almost no signal until the whole task is solved, so exploration, credit assignment and curriculum become the bottleneck rather than optimization. I attack this from two directions that turn out to be the same problem: goal-conditioned and model-based RL for embodied agents, and RL post-training for large models, where a long reasoning trajectory is likewise graded by one outcome-level reward at the very end.
- Sparse-Reward RL & Agent Learning: goal-conditioned RL, goal-directed exploration, model-based RL and world models, learning from demonstrations, automatic curriculum and subgoal discovery.
- RL Post-Training for LLMs: SFT and RL post-training with PPO, GRPO and preference-based objectives for reasoning; reward design and credit assignment under long-horizon, outcome-only supervision. I have post-trained 4B-scale models with SFT / PPO / GRPO on mathematical reasoning tasks.
- Vision-Language Models & Embodied Agents: VLMs for robotics, VLMs for RL, large world models, and program synthesis for interpretable robot policies.
- Machine Learning in Healthcare: survival and causal modeling (Cox regression, DID, ISM, etc.), and interpretability.
News
| [08/2026] | Finished my summer internship at TikTok (San Jose, CA) as a Machine Learning Scientist Intern. |
| [05/2026] | Started my summer internship at TikTok (San Jose, CA) as a Machine Learning Scientist Intern. |
| [01/2026] | One paper was accepted by ICLR 2026. |
| [09/2025] | One paper was accepted by NeurIPS 2025. |
| [09/2025] | One paper was accepted by OOPSLA 2025. |
| [09/2024] | Two papers were accepted by NeurIPS 2024. |
| [09/2024] | One paper was accepted by EMNLP 2024. |
| [09/2023] | Begin my journey of PhD study at Rutgers |
| [06/2022] | Begin my research in General Medical Center of West China Hospital, Sichuan University |
Publications
Conference Papers
Preference-based Policy Optimization from Sparse-reward Offline Dataset
Wenjie Qiu, Guofeng Cui, Shicheng Liu, Yuanlin Duan and He Zhu
International Conference on Learning Representations (ICLR), 2026
[Paper][Poster]
Learning from Demonstrations via Capability-Aware Goal Sampling
Yuanlin Duan, Yuning Wang, Wenjie Qiu and He Zhu
Neural Information Processing Systems (NeurIPS), 2025
[Paper][Poster]
Abstraction Refinement-guided Program Synthesis for Robot Learning from Demonstrations
Guofeng Cui, Yuning Wang, Wensen Mao, Yuanlin Duan and He Zhu
The OOPSLA issue of the Proceedings of the ACM on Programming Languages, OOPSLA 2025
[Paper][Artifact]
Learning World Models for Unconstrained Goal Navigation
Yuanlin Duan, Wensen Mao and He Zhu
Neural Information Processing Systems (NeurIPS), 2024
[Paper][Poster]
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
Yuanlin Duan, Guofeng Cui and He Zhu
Neural Information Processing Systems (NeurIPS), 2024
[Paper][Poster]
MoE-I²: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
Cheng Yang, Yang Sui, Jinqi Xiao, Lingyi Huang, Yu Gong, Yuanlin Duan, Wenqi Jia, Miao Yin, Yu Cheng, Bo Yuan
Findings of the Association for Computational Linguistics: EMNLP 2024
[Paper][ACL Anthology]
Experience
|
TikTok, San Jose, CA, USA Machine Learning Scientist Intern, May 2026 - Aug 2026 |
|
General Medical Center of West China Hospital, Chengdu, China Research Assistant, Jun 2022 - Aug 2023 |
Teaching
Teaching Assistant
| Fall | 2024 | Teaching Assistant | CS336: Principles of Information and Data Management |
| Spring | 2024 | Teaching Assistant | CS210: Data Management for Data Science |
| Fall | 2023 | Teaching Assistant | CS210: Data Management for Data Science |
Service
-
Reviewer:
NeurIPS 2025, NeurIPS 2026.
Personal
- I am very happy to communicate with others about everything related to life, academics, and entrepreneurship.
- I am a follower of value investing and welcome discussions about perspectives on great businesses.
- I'm a badminton beginner and would love to find someone of a similar skill level to play with!