Yu Li
George Washington University, Washington, D.C. 2025.9– Present
Wuhan University, Hongyi Honor College, China 2021.9-2025.5
Research Topics: Reinforcement Learning • Post-Training • Generative AI
I am currently a first-year Ph.D. candidatein the ECE Department at George Washington University supervised by Prof. Tian Lan and work with Prof.Zhengling Qi. I obtained my B.Eng. degree from Hongyi Honor College of Wuhan University.
My research interests focus on Generative AI, Reinforcement Learning (RL), and Post-training methods for LLMs. I am always open to communication and collaboration.
- 📄 CV
- 🧪 GitHub
- 🎓 Google Scholar
News
- [02/2026] One paper was accepted at 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] Our work KG-SAM: Injecting Anatomical Knowledge into Segment Anything Models via Conditional Random Fields was accepted at ICASSP 2026 🎉.
- [11/2025] Our work Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT was accepted at AAAI 2026 🎉.
- [05/2025] Graduated from Wuhan University, goodbye to my home university 👋.
Publications
Preprint / Under Review
Unlocking Implicit Self-Reflection in Preference Optimization for LLM Alignment
· Paper · Code
· Paper · Code
Preference optimization that leverages implicit self-reflection signals in pairwise data to improve LLM alignment.
DPOSimPOPreference Learning
Aligning LLMs with Finite State Machine Logic for Multi-turn Verilog Code Generation
Structured alignment to teach LLMs finite-state transition logic for multi-turn Verilog generation.
RLVRCode GenerationVerilog FSM
CRAFT-LORA: Content-Style Personalization via Rank-Constrained Adaptation
Rank-constrained LoRA adaptation for content–style personalization in image generation.
Generative AIPersonalizationLoRA
Conferences
KG-SAM: Injecting Anatomical Knowledge into Segment Anything Models via Conditional Random Fields
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
A unified calibration+rotation weight-conditioning framework that improves PEFT performance and efficiency.
LLMs PEFTWeight Conditioning
Journals
Dual branch SAM-Transformer Fusion Network for Accurate Breast Ultrasound Image Segmentation
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
Self-supervised monocular depth estimation for endoscopy using diffusion models with teacher-guided distillation.
Depth EstimationDiffusion ModelDistillation
Experiences
Mobile Intelligence Lab, George Washington University
Artificial General Intelligence Lab, Westlake University
Cyber-Physical Systems Lab, UC Irvine
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.
Skills
- Languages: English (TOEFL 105), Chinese (Native), Japanese (N5)
- Programming: Python, C/C++, Matlab, Verilog
- Tools & Platforms: Ubuntu, Docker, Pytorch, Tensorflow, Git, Cadence
This website was stolen from my best friend CD.