4 papers
MV-CoRe: Multimodal Visual-Conceptual Reasoning for Complex Visual Question Answering
Jingwei Peng, Jiehao Chen, Mateo Alejandro Rojas +1
Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for exist…
Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs
Rafael Carranza, Mateo Alejandro Rojas
This paper introduces a novel approach to Dialogue State Tracking (DST) that leverages Large Language Models (LLMs) to generate natural language descriptions of dialogue states, mo…
Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning
Mateo Alejandro Rojas, Rafael Carranza
Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resou…
Enhancing Scientific Figure Captioning Through Cross-modal Learning
Mateo Alejandro Rojas, Rafael Carranza
Scientific charts are essential tools for effectively communicating research findings, serving as a vital medium for conveying information and revealing data patterns. With the rap…