What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect…
MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistantsby Hritik Bansal, Daniel Israel, Siyan Zhao, Shufan…
BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific…
TANGO: Training-free Embodied AI Agents for Open-world Tasksby Filippo Ziliotto, Tommaso Campari, Luciano Serafini, Lamberto…
RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sectorby Zhensheng Wang, Wenmian…
VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generationby Hyeonseok Lim, Dongjae Shin, Seohyun Song,…
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingby Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao…
Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answeringby Sai Bhargav…
Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicineby Xiaoshuang Huang, Lingdong Shen,…
Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answeringby Wonjin Lee,…