Examining the Commitments and Difficulties Inherent in Multimodal Foundation Models for Street View Imageryby Zhenyuan…
Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Modelsby Shenglin Zhang, Pengtian…
Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answeringby Xiaoming Zhang, Ming Wang, Xiaocui…
Multimodal Datasets and Benchmarks for Reasoning about Dynamic Spatio-Temporality in Everyday Environmentsby Takanori Ugai, Kensho…
RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphsby Mayank Kharbanda,…
Differentiating Choices via Commonality for Multiple-Choice Question Answeringby Wenqing Deng, Zhe Wang, Kewen Wang, Shirui…
Large Language Model Driven Recommendationby Anton Korikov, Scott Sanner, Yashar Deldjoo, Zhankui He, Julian McAuley,…
CoDi: Conversational Distillation for Grounded Question Answeringby Patrick Huber, Arash Einolghozati, Rylan Conway, Kanika Narang,…
V-RoAst: A New Dataset for Visual Road Assessmentby Natchapon Jongwiriyanurak, Zichao Zeng, June Moh Goo,…
Putting People in LLMs’ Shoes: Generating Better Answers via Question Rewriterby Junhao Chen, Bowen Wang,…