Are VLMs Really Blind
원문 초록
Vision Language Models excel in handling a wide range of complex tasks, including Optical Character Recognition (OCR), Visual Question Answering (VQA), and advanced geometric reasoning. However, these models fail to perform well on low-level basic visual tasks which are especially easy for humans. Our goal in this work was to determine if these models are truly "blind" to geometric reasoning or if there are ways to enhance their capabilities in this area. Our work presents a novel automatic pipeline designed to extract key information from images in response to specific questions. Instead of just relying on direct VQA, we use question-derived keywords to create a caption that highlights important details in the image related to the question. This caption is then used by a language model to provide a precise answer to the question without requiring external fine-tuning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Describe Anything Model for Visual Question Answering on Text-rich Images
SeqPE: Transformer with Sequential Position Encoding
Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
토론
이 논문과 연결된 포럼 글이 아직 없습니다.