Cover Image

Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zou, Hongjian, Ge, Yue, Ding, Qi, Liao, Yixuan, Chen, Xiaoxin
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs
by: Su, Xin, et al.
Published: (2024)

VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery
by: Ge, Jinchao, et al.
Published: (2025)

Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions
by: Rostamkhani, Mohammadmostafa, et al.
Published: (2024)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
by: Li, Yangfu, et al.
Published: (2025)

Knowledge Generation for Zero-shot Knowledge-based VQA
by: Cao, Rui, et al.
Published: (2024)

Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry
by: Hou, Wenjun, et al.
Published: (2024)

Multimodal LLM With Hierarchical Mixture-of-Experts for VQA on 3D Brain MRI
by: Vepa, Arvind Murari, et al.
Published: (2025)

Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA
by: Fan, Yue, et al.
Published: (2024)

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge
by: Wang, Haibo, et al.
Published: (2024)

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
by: Yanuka, Moran, et al.
Published: (2024)

MTA: Multimodal Task Alignment for BEV Perception and Captioning
by: Ma, Yunsheng, et al.
Published: (2024)

Efficient Whole Slide Pathology VQA via Token Compression
by: Lyu, Weimin, et al.
Published: (2025)

VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering
by: Sood, Ekta, et al.
Published: (2021)

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
by: Xing, Long, et al.
Published: (2025)

OmniCaptioner: One Captioner to Rule Them All
by: Lu, Yiting, et al.
Published: (2025)

When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA
by: Tuchinda, Pume, et al.
Published: (2025)

IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
by: Shahgir, Haz Sameen, et al.
Published: (2024)

EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning
by: Zhang, Junzhe, et al.
Published: (2024)

Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts
by: Xu, Run, et al.
Published: (2026)

Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA
by: Karim, A H M Rezaul, et al.
Published: (2025)

GRAM: Global Reasoning for Multi-Page VQA
by: Blau, Tsachi, et al.
Published: (2024)

Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering
by: Wang, Haibo, et al.
Published: (2024)

Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization
by: Tang, Changli, et al.
Published: (2024)

Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions
by: Möller, Lucas, et al.
Published: (2024)

RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events
by: Chen, Zhenyuan, et al.
Published: (2025)

GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
by: Ma, Ziyu, et al.
Published: (2024)

Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags
by: Qi, Daiqing, et al.
Published: (2024)

video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models
by: Tang, Changli, et al.
Published: (2025)

Multimodal Arabic Captioning with Interpretable Visual Concept Integration
by: Elchafei, Passant, et al.
Published: (2025)

CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
by: Bajpai, Divya Jyoti, et al.
Published: (2024)

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
by: Ma, Dongsheng, et al.
Published: (2026)

CommVQA: Situating Visual Question Answering in Communicative Contexts
by: Naik, Nandita Shankar, et al.
Published: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
by: Liang, Jianxin, et al.
Published: (2025)

MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
by: Baek, Jeonghun, et al.
Published: (2025)

Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning
by: Chaffin, Antoine, et al.
Published: (2024)

Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention
by: Nguyen, Nhi Ngoc-Yen, et al.
Published: (2026)

Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches
by: Sterner, Igor, et al.
Published: (2024)

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
by: Jia, Yiming, et al.
Published: (2025)

Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals
by: Wu, Te-Lin, et al.
Published: (2021)

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
by: Guo, Jarvis, et al.
Published: (2024)