Yifan Zeng
PhD Student in AI 🔮
Hi! I’m Yifan Zeng and my name in Chinese is 曾一凡 . I’m currently a third-year Computer Science Ph.D. student at Oregon State University, where I’m fortunate to be advised by Huazheng Wang.
My research focuses on the robust planning and decision-making of large language models (LLMs). I’m passionate about developing Agentic AI through reinforcement learning and multi-agent systems.
Before joining OSU, I worked as a Research Scientist at a technology startup, where I carried out AI solutions using deep learning and computer vision. My previous research spans object detection, medical image analysis, representation learning, and AI4Science. I received my B.Eng. in Data Science at Zhuhai College of Jilin University in 2023, ranking first in my department with a 3.84/4.0 GPA.
Publications & Preprints
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Modeling the Time Evolution of Compact Binary Systems with Machine Learning
Enhanced object detection in pediatric bronchoscopy images using YOLO-based algorithms with CBAM attention mechanism
Task-Level Consistency Semi-supervised Based Domain Adaptation for Lung Nodules Segmentation
A challenge of deep‐learning‐based object detection for hair follicle dataset
✧ Equal Contribution / Leading Contributors
The papers listed are sorted by the completion date of the initial version.
