Yu Li

George Washington University, Washington, D.C.

Ph.D. in Electrical and Computer Engineering (GPA: 4.0/4.0)

2025.9 – 2029.5

Wuhan University, Hongyi Honor College, China

B.Eng. in Microelectronics Science and Technology (GPA: 3.87/4.0)

2021.9 – 2025.5

Second-year Ph.D. candidate at GWU, supervised by Prof. Tian Lan and working with Prof. Zhengling Qi.

LLM Post-Training · Agent Policy Learning · Generative AI

📄 CV GitHub Google Scholar LinkedIn

News

07/2026MomentKV is accepted to COLM 2026 🎉. See you in San Francisco.

06/2026Started serving as a reviewer for TMLR.

05/2026Joining ByteDance as a Research Scientist Intern in San Jose, May–August 🚀.

04/2026T-STAR is accepted to ACL 2026 🎉. See you in San Diego.

02/2026CRAFT-LoRA is accepted to CVPR 2026 🎉.

01/2026Passed the Ph.D. qualifying exam and am now a Ph.D. candidate 🎓.

01/2026KG-SAM is accepted to ICASSP 2026 as an Oral paper 🎉.

Publications

Preprint / Under Review

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning

Yu Li, Rui Miao, Tian Lan, Zhengling Qi

Under review at NeurIPS 2026 · Paper

ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning

Yu Li, Rui Miao, Zhengling Qi, Tian Lan

Under review at NeurIPS 2026 · Paper · Code

Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO

Yu Li, Tian Lan, Zhengling Qi

Under review at NeurIPS 2026 · Paper · Code

InsPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization

Yu Li, Tian Lan, Zhengling Qi

Under review at NeurIPS 2026 · RSI@ICLR 2026 (Poster) · Paper · Code

Conferences

Prompted Information Bottlenecks: Rethinking Layer-Wise Information Allocation in Frozen Vision Transformers

Yuqi Li, Xi Xiao, Yunbei Zhang, Lin Zhao, Yu Li, Aiden Zhao, Tianyang Wang, Hao Xu, Yingli Tian

ACM MM 2026

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference

Yu Li, Binxu Li, Tian Lan

COLM 2026 · Paper

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization

Yu Li, Sizhe Tang, Tian Lan

ACL Findings 2026

CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion

Yu Li, Yujun Cai, Chi Zhang

CVPR 2026 · Paper · Code

ACDZero: MCTS Agent for Mastering Automated Cyber Defense

Yu Li*, Sizhe Tang*, Rongqian Chen, Fei Xu Yu, Guangyu Jiang, Mahdi Imani, Nathaniel D. Bastian, Tian Lan

ICCN@INFOCOM 2026 · *Equal contribution · Paper · Code

KG-SAM: Injecting Anatomical Knowledge into Segment Anything Models via Conditional Random Fields

Yu Li, Chang Da, Xi Xiao

ICASSP 2026 · Oral · Paper

Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT

Chang Da, Peng Xue, Yu Li, Yongxiang Liu, Pengxiang Xu, Shixun Zhang

AAAI 2026 · Paper · Code

Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer

Yu Li*, Chang Da*

ICONIP 2024 · *Equal contribution · Paper · Code

Journals

Dual branch SAM-Transformer Fusion Network for Accurate Breast Ultrasound Image Segmentation

Y. Li, J. Huang et al.

Medical Physics, JCR Q1, 2025 · Paper · Code

SfMDiffusion: Self-supervised Monocular Depth Estimation in Endoscopy Based on Diffusion Models

Y. Li, D. Chang et al.

IJCARS, JCR Q2, 2025 · Paper · Code

Experiences

2025.8 – Present

Mobile Intelligence Lab, GWU Post-training, RL, Reasoning · Prof. Tian Lan

2025.3 – 2025.7

AGI Lab, Westlake University Generative AI · Prof. Chi Zhang

2024.6 – 2024.10

Cyber-Physical Systems Lab, UC Irvine Multimodal Uncertainty Fusion · Prof. Mohammad Al Faruque

Honors and Awards

• ICML 2026 Gold Reviewer (Top Reviewers Recognition)
• Innova International Exchange Scholarship, Wuhan University, 2024
• Innova Excellence Scholarship (Top 3%), Wuhan University, 2023, 2024
• Academic Excellence Scholarship (Top 5%), Hongyi Honor College, 2022–2024
• First-Class Scholarship (Top 5%), Wuhan University, 2022–2024
• Patent: Energy-saving calculation method, CN116085952

Academic Services

The peer review mechanism is breaking down, but conscientious peer review endures.

• Conference: NeurIPS’26, COLM’26, ACM MM’26, ICML’26, ICLR’26, AAAI’26, ICASSP’26
• Journal: TMLR, TPAMI, ToN, Neurocomputing

This website was stolen from my best friend CD.