paper-with-me

Papers

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

2024-03-17 · Guohao Sun, Can Qin, Jiamian Wang, Zeyuan Chen, ran Xu, Zhiqiang Tao

Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which, however, is costly to obtain and has not thoroughly explored the rich contextual information contained in images. This paper first attempts to harness the overlooked context within visual instruction data, training the model to self-supervised "learning" how to ask high-quality questions. In this way, we introduce a novel framework named SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant. SQ-LLaVA exhibits proficiency in generating flexible and meaningful image-related questions while analyzing the visual clue and prior language knowledge, signifying an advanced level of generalized visual understanding. Moreover, fine-tuning SQ-LLaVA on higher-quality instruction data shows a performance improvement compared with traditional visual-instruction tuning methods. This improvement highlights the efficacy of self-questioning techniques in achieving a deeper and more nuanced comprehension of visual content across various contexts.

📄 PDF Abstract BibTeX arXiv:2403.11299

Code (2)

heliossun/sq-llava 공식 구현 pytorch
heliossun/stllava-med pytorch

Tasks

Language ModellingQuestion AnsweringSelf-Supervised LearningVisual Question Answering

Similar Papers 제목 키워드 기반

CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario

2024-05-06 · Zhizhao Duan, Hao Cheng, Duo Xu, Xi Wu 외

In the vast and dynamic landscape of urban settings, Traffic Safety Description and Analysis plays a pivotal role in applications ranging from insurance inspection to accident prevention. This paper introduces CityLLaVA,…

PositionPredictionPrompt Engineering

Counterfactual Self-Questioning for Stable Policy Optimization in Language Models

2025-12-31 · Mandar Parab arxiv

Recent work on language model self-improvement shows that models can refine their own reasoning through reflection, verification, debate, or self-generated rewards. However, most existing approaches rely on external crit…

Mathematical Reasoning

STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering

2024-06-28 · Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang 외

Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning crit…

Medical DiagnosisMedical Question AnsweringMedical Visual Question AnsweringQuestion Answering+2

LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day

2023-06-01 · NeurIPS 2023 11 · Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama 외

Conversational generative AI has demonstrated remarkable promise for empowering biomedical practitioners, but current investigations focus on unimodal text. Multimodal conversational AI has seen rapid progress by leverag…

Image ClassificationInstruction FollowingLanguage ModellingQuestion Answering+3

Self-Questioning Vision-Language Models: Reinforcement Learning for Compositional Visual Reasoning

2026-06-14 · Saraswathy Amjith arxiv

Vision-Language Models (VLMs) are AI systems that process both images and text, yet they often struggle with compositional visual reasoning questions that require chaining multiple steps together, such as identifying obj…

Reinforcement LearningVisual Reasoning