Yunqi Hong

yunqihong@ucla.edu

I am a second-year PhD student in the Computer Science Department at UCLA, advised by Prof. Cho-Jui Hsieh.

My research focuses on LLM post-training, inferencing, and downstream applications. I am currently working on LLM reinforcement learning, reward modeling, and text-to-image generation. Previously, I explored topics in LLM automatic prompting, model interpretability, graph adversarial attacks, and recommender systems.

I also collaborate with Prof. Neil Y.C. Lin on developing LLM-driven methods for biomedical research.

selected publications

NeurIPS 2025

Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs

Yunqi Hong, Sohyun An, Andrew Bai, Neil YC Lin, and 1 more author

Advances in Neural Information Processing Systems, 2025

Abs PDF Code

Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to distinguish between visually similar subcategories–details that MLLMs may easily overlook without explicit guidance. To address this, we introduce AutoSEP, an iterative self-supervised prompt learning framework designed to enhance MLLM fine-grained classification capabilities in a fully unsupervised manner. Our core idea is to leverage unlabeled data to learn a description prompt that guides MLLMs in identifying crucial discriminative features within an image, and boosts classification accuracy. We developed an automatic self-enhancing prompt learning framework called AutoSEP to iteratively improve the description prompt using unlabeled data, based on instance-level classification scoring function. AutoSEP only requires black-box access to MLLMs, eliminating the need for any training or fine-tuning. We evaluate our approach on multiple fine-grained classification datasets. It consistently outperforms other unsupervised baselines, demonstrating the effectiveness of our self-supervised optimization framework. Notably, AutoSEP on average improves 13 percent over standard zero-shot classification and 5 percent over the best-performing baselines.
Preprint

IRIS: Intrinsic Reward Image Synthesis

Yihang Chen, Yuanhao Ban, Yunqi Hong, and Cho-Jui Hsieh

arXiv preprint arXiv:2509.25562, 2025

Abs PDF

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in language reasoning, its application to autoregressive Text-to-Image (T2I) generation is often constrained by the limited availability of human preference data. This paper explores how an autoregressive T2I model can learn from internal signals without relying on external rewards or labeled data. Contrary to recent findings in text generation, we show that maximizing self-uncertainty, rather than self-certainty, improves image generation. We observe that this is because autoregressive T2I models with low uncertainty tend to generate simple and uniform images, which are less aligned with human preferences. Based on these observations, we propose IRIS (Intrinsic Reward Image Synthesis), the first framework to improve autoregressive T2I models with reinforcement learning using only an intrinsic reward. Empirical results demonstrate that applying IRIS to autoregressive T2I models achieves performance that is competitive with or superior to external rewards.