Publications

My research focuses on LLM alignment, reasoning, and post-training optimization. On the algorithmic side, I work on DPO-based optimization (RPO, SAPO, Diffusion-RPO) and PPO-based optimization (Segment-Level PPO) to improve model alignment and reasoning reliability. On the data side, I develop ContextCheck, a sentence-level faithfulness verifier designed for context-dependent hallucination detection, and also contribute to KODCODE, a large-scale and verifiable dataset for code generation model training.

6+ first/co-first author works • CVPR, ICCV, TMLR, ACL Findings • 🏆 Best Paper Award at DataWorld @ ICML 2025

2025

Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model

TMLR25 Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model

Yueqin Yin*, Shentao Yang*, Yujia Xie, Ziyi Yang, Yuting Sun, Hany Awadalla, Weizhu Chen, Mingyuan Zhou

Paper / Code

KODCODE: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

ACL Findings25 🏆 Best Paper Award at DataWorld @ ICML 2025 KODCODE: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

Zhangchen Xu, Yang Liu, Yueqin Yin, Mingyuan Zhou, Radha Poovendran

Paper / Code / Website

ContextCheck: Sentence-Level Faithfulness Verification with Context-Aware Disambiguation

Under Review ContextCheck: Sentence-Level Faithfulness Verification with Context-Aware Disambiguation

Yueqin Yin, Yaxi Li, Xin Liu, Xun Wang, Kaiqiang Song, Simin Ma, Shujian Liu, Sathish Reddy Indurthi, Haoyun Deng, Pengcheng He, Mingyuan Zhou, Song Wang

Paper (Coming Soon) / Code (Coming Soon)

2024

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

arXiv'2402 Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

Yueqin Yin*, Zhendong Wang*, Yi Gu, Hai Huang, Weizhu Chen, Mingyuan Zhou

Paper / Code

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment

arXiv'2405 Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment

Yueqin Yin*, Zhendong Wang*, Yujia Xie, Weizhu Chen, Mingyuan Zhou

Paper / Code

Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization

arXiv'2406 Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization

Yi Gu, Zhendong Wang, Yueqin Yin, Yujia Xie, Mingyuan Zhou

Paper

2023

Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers

ICCV23 Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers

Shiyue Cao, Yueqin Yin, Lianghu Huang, Yu Liu, Xin Zhao, Deli Zhao, Kaiqi Huang

Paper

2022

TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

CVPR22 TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

Yanbo Xu*, Yueqin Yin*, Liming Jiang, Qianyi Wu, Chengyao Zheng, Chen Change Loy, Bo Dai, Wayne Wu

Paper / Code / Website

DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models

CSAI22 DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models

Yueqin Yin, Lianghua Huang, Yu Liu, Kaiqi Huang

Paper