SOTAVerified

Visual Question Answering

MLLM Leaderboard

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 851–900 of 2177 papers

TitleStatusHype
Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering—0
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models—0
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning—0
Aligning Modalities in Vision Large Language Models via Preference Fine-tuningCode2
ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language ModelsCode3
CoLLaVO: Crayon Large Language and Vision mOdelCode2
II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question AnsweringCode0
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models—0
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language ModelsCode1
PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter—0
Prompt-based Personalized Federated Learning for Medical Visual Question Answering—0
Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-raysCode0
OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMCode4
Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models—0
PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal RetrieversCode3
Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks—0
Visually Dehallucinative Instruction GenerationCode0
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language ModelsCode4
Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image DataCode0
PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs—0
Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to PairsCode3
Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyCode1
Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & HallucinationsCode1
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive SurveyCode3
CIC: A Framework for Culturally-Aware Image Captioning—0
Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel ImagesCode0
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language ModelsCode7
Convincing Rationales for Visual Question Answering ReasoningCode0
Text-Guided Image ClusteringCode1
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional TokenizationCode4
GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question AnsweringCode2
Knowledge Generation for Zero-shot Knowledge-based VQACode0
Instruction Makes a DifferenceCode0
Can Generative AI Support Patients' & Caregivers' Informational Needs? Towards Task-Centric Evaluation Of AI Systems—0
From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information—0
MouSi: Poly-Visual-Expert Vision-Language ModelsCode2
InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model—0
Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA—0
MoE-LLaVA: Mixture of Experts for Large Vision-Language ModelsCode7
LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering—0
Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning—0
Free Form Medical Visual Question Answering in Radiology—0
Small Language Model Meets with Reinforced Vision Vocabulary—0
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities—0
Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World KnowledgeCode1
Veagle: Advancements in Multimodal Representation LearningCode1
Question-Answer Cross Language Image Matching for Weakly Supervised Semantic SegmentationCode1
COCO is "ALL'' You Need for Visual Instruction Fine-tuning—0
Uncovering the Full Potential of Visual Grounding Methods in VQACode0
BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining—0
Show:102550
← PrevPage 18 of 44Next →
All datasetsMM-VetViP-BenchVQA v2 test-devBenchLMMMMBenchV*benchVQA v2 valMSRVTT-QAVQA v2 test-stdMMHal-BenchMSVD-QAPlotQA-D1

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMCTAgent (GPT-4 + GPT-4V)GPT-4 score74.24—Unverified
2Qwen2-VL-72BGPT-4 score74—Unverified
3InternVL2.5-78BGPT-4 score72.3—Unverified
4GPT-4o +text rationale +IoTGPT-4 score72.2—Unverified
5Lyra-ProGPT-4 score71.4—Unverified
6GLM-4V-PlusGPT-4 score71.1—Unverified
7Phantom-7BGPT-4 score70.8—Unverified
8InternVL2.5-38BGPT-4 score68.8—Unverified
9InternVL2-26B (SGP, token ratio 64%)GPT-4 score65.6—Unverified
10Baichuan-Omni (7B)GPT-4 score65.4—Unverified