Yu Li

George Washington University, Washington, D.C. 2025.9–2029.5(expected)

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

Wuhan University, Hongyi Honor College, China 2021.9-2025.5

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

I am currently a first year Ph.D. candidate at GWU supervised by Prof. Tian Lan and work with Prof.Zhengling Qi.

Research Topics: LLM Post-Training • Agent Policy Learning • Generative AI

• 📄 CV
• 🧪 GitHub
• 🎓 Google Scholar
• 💼 LinkedIn

---

News

• [03/2026] InsPO is accepted to AI with Recursive Self-Improvement@ICLR 2026 🎉. See you in Rio!
• [02/2026] CRAFT-LORA is accepted to CVPR 2026 🎉. See you in Denver.
• [02/2026] ACDZero is accepted to ICCN@INFOCOM2026 🎉. See you in Tokyo.
• [01/2026] I passed my PhD qualifying exam in my first semester and am now a PhD candidate 🎓.
• [01/2026] KG-SAM is accepted to ICASSP 2026 as an Oral Paper 🎉.
• [11/2025] SoRA is accepted to AAAI 2026 🎉.

---

Publications

Preprint / Under Review

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

Yu Li, Rui Miao, Zhengling Qi, Tian Lan

Under review at COLM 2026 · Code

Hierarchical RL framework with intrinsic skill evolution for scalable agent reasoning.

Hierarchical RLAgentSkill Learning

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

Yu Li, Tian Lan, Zhengling Qi

Under review at ICML 2026 · Code

Bilateral context conditioning and reward-confidence correction to improve GRPO training.

GRPORLHFPost-training

InsPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization

Yu Li, Tian Lan, Zhengling Qi

Under review at ICML 2026 · AI with Recursive Self-Improvement@ICLR 2026 (Poster) · Paper · Code

Preference optimization that leverages intrinsic self-reflection signals in pairwise data to improve LLM alignment.

DPOSimPOPreference Learning

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

Yu Li, Sizhe Tang, Tian Lan

Under review at ACL 2026

Self-rectification and tree-based grafting for multi-turn agent policy optimization.

AgentMulti-turnPolicy Optimization

MultiRefine-V: Multi-Turn Reinforcement Learning for Enhancing Verilog Code Synthesis

Qiufeng Li, Yu Li, Shu Hong, Tian Lan, Weidong Cao

Under review

Multi-turn RL for enhancing Verilog code synthesis quality.

RLVRCode GenerationVerilog

Conferences

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

Yu Li, Yujun Cai, Chi Zhang

CVPR 2026 · Paper

Rank-constrained LoRA adaptation for content–style personalization in image generation.

Generative AIPersonalizationLoRA

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

(*:Equal contribution)

ICCN@INFOCOM 2026 · Paper · Code

Graph-embedding-guided MCTS planning for sample-efficient automated cyber defense.

Cyber DefenseMCTSGNN

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

Yu Li, Chang Da, Xi Xiao

ICASSP 2026 · Oral · Paper · Code

Knowledge-guided SAM with anatomical priors and CRF refinement for robust medical image segmentation.

Medical SegmentationSAMKnowledge GraphCRF

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

A unified calibration+rotation weight-conditioning framework that improves PEFT performance and efficiency.

LLMs PEFTWeight Conditioning

Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer

Yu Li*, Chang Da*

(*:Equal contribution)

ICONIP 2024 · Paper · Code

TrOCR-based mixed-text OCR with efficient PEFT and an end-to-end evaluation pipeline.

OCRLoRA

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

Dual-branch SAM–Transformer fusion for accurate breast ultrasound image segmentation.

Ultrasound SegmentationSAMTransformer

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

Y. Li, D. Chang et al.

International Journal of Computer Assisted Radiology and Surgery, JCR Q2, 2025 · Paper · Code

Self-supervised monocular depth estimation for endoscopy using diffusion models with teacher-guided distillation.

Depth EstimationDiffusion ModelDistillation

---

Experiences

Mobile Intelligence Lab, George Washington University

Research Topic: Post-training, RL, Reasoning

Advisor: Prof. Tian Lan · Aug. 2025 – Present

Artificial General Intelligence Lab, Westlake University

Research Topic: Generative AI

Advisor: Prof. Chi Zhang · Mar. 2025 – Jul. 2025

Cyber-Physical Systems Lab, UC Irvine

Research Topic: Multimodal Uncertainty Fusion

Advisor: Prof. Mohammad Al Faruque · Jun. 2024 – Oct. 2024

---

Honors and Awards

• 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, 2023, 2024
• First-Class Scholarship (Top 5%), Wuhan University, 2022, 2023, 2024
• Patent: Energy-saving calculation method, CN116085952.

---

Academic Services

• Conference Reviewer: ICML’26, CVPR’26, ICLR’26, AAAI’26, ICASSP’26
• Journal Reviewer: Neurocomputing, Frontiers in Oncology, IEEE Transactions on Networking, Frontiers in Medicine

This website was stolen from my best friend CD.