7 papers
When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models
Haoran Zhao, Soyeon Caren Han, Eduard Hovy
Multimodal language models are typically evaluated through external behavior: selecting the correct image--text match, rejecting unsupported captions, or answering visual queries c…
ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
Shuo Yang, Soyeon Caren Han, Yihao Ding +2
Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, curren…
UniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecasting
Sehyuk Park, Soyeon Caren Han, Eduard Hovy
Time series forecasting underpins applications in finance, healthcare, and environmental monitoring. Despite the success of Time Series Foundation Models (TSFMs), existing approach…
EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
Shuo Yang, Soyeon Caren Han, Xueqi Ma +3
LLM-based agents depend on effective tool-use policies to solve complex tasks, yet optimizing these policies remains challenging due to delayed supervision and the difficulty of cr…
When Is Rank-1 Enough? Geometry-Guided Initialization for Parameter-Efficient Fine-Tuning
Haoran Zhao, Soyeon Caren Han, Eduard Hovy
Parameter-efficient fine-tuning (PEFT) is a standard way to adapt multimodal large language models, yet extremely low-rank settings -- especially rank-1 LoRA -- are often unstable.…
MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering
Shuo Yang, Siwen Luo, Soyeon Caren Han +1
Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limit…