5 papers
Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
Yige Xu, Yongjie Wang, Zizhuo Wu +3
Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear…
Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?
Yongjie Wang, Yibo Wang, Xin Zhou +1
Probing techniques have shown promise in revealing how LLMs encode human-interpretable concepts, particularly when applied to curated datasets. However, the factors governing a dat…
RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval
Yongjie Wang, Jonathan Leung, Zhiqi Shen
Large Language Models (LLMs) have shown promise in character imitation, enabling immersive and engaging conversations. However, they often generate content that is irrelevant or in…
From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft
Jonathan Leung, Yongjie Wang, Zhiqi Shen
Large Language Models (LLMs) demonstrate impressive general capabilities but often struggle with step-by-step procedural reasoning, a critical challenge in complex interactive envi…
An Intelligent and Privacy-Preserving Digital Twin Model for Aging-in-Place
Yongjie Wang, Jonathan Cyril Leung, Ming Chen +4
The population of older adults is steadily increasing, with a strong preference for aging-in-place rather than moving to care facilities. Consequently, supporting this growing demo…