activity
20242026
collaborators

7 papers

cs.CV2026

VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation

Seongheon Park, Changdae Oh, Hyeong Kyu Choi +2

Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's abili…

cs.CL2025

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Leitian Tao, Xuefeng Du, Sharon Li

Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesi…

cs.AI2025

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach

Changdae Oh, Zhen Fang, Shawn Im +2

Multimodal large language models (MLLMs) have shown promising capabilities but struggle under distribution shifts, where evaluation data differ from instruction tuning distribution…

cs.LG2025

Steer LLM Latents for Hallucination Detection

Seongheon Park, Xuefeng Du, Min-Hsuan Yeh +2

Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination d…

cs.LG2025

Foundations of Unknown-aware Machine Learning

Xuefeng Du

Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical f…

cs.CL2025

Challenges and Future Directions of Data-Centric AI Alignment

Min-Hsuan Yeh, Jeffrey Wang, Xuefeng Du +4

As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignmen…