7 papers
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Changdae Oh, Wendi Li, Seongheon Park +3
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irrever…
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
Seongheon Park, Wendi Li, Changdae Oh +4
Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that…
How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
Shawn Im, Changdae Oh, Zhen Fang +1
Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and g…
Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
Changdae Oh, Seongheon Park, To Eun Kim +8
Uncertainty quantification (UQ) for large language models (LLMs) is a key building block for safety guardrails of daily LLM applications. Yet, even as LLM agents are increasingly d…
General Exploratory Bonus for Optimistic Exploration in RLHF
Wendi Li, Changdae Oh, Sharon Li
Optimistic exploration is central to improving sample efficiency in reinforcement learning with human feedback, yet existing exploratory bonus methods to incentivize exploration of…
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Lin Long, Changdae Oh, Seongheon Park +1
Large vision-language models (LVLMs) achieve strong performance on multimodal tasks, yet they often default to their language prior (LP) -- memorized textual patterns from pre-trai…