발행물
컨퍼런스
Seminar | Data Science Lab
2025
,
Multimodal Procedural Planning via Dual Text-Image Prompting
2024
Retrieval Augmented Geneartion or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
VisualWebArena: Evaluating Multimodal Agents on Realistic Visually Grounded Web Tasks
Guiding a Diffusion Model with a Bad Version of Itself
The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation