Visual Reasoning with Natural Language
원문 초록
Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world. Such reasoning over language and vision is an open problem that is receiving increasing attention. While existing data sets focus on visual diversity, they do not display the full range of natural language expressions, such as counting, set reasoning, and comparisons. We propose a simple task for natural language visual reasoning, where images are paired with descriptive statements. The task is to predict if a statement is true for the given scene. This abstract describes our existing synthetic images corpus and our current work on collecting real vision data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection
Describe Anything Model for Visual Question Answering on Text-rich Images
Assay2Mol: large language model-based drug design using BioAssay context
Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.