SOTAVerified

Multimodal Reasoning

Reasoning over multimodal inputs.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 302 papers

TitleStatusHype
Question-Aware Gaussian Experts for Audio-Visual Question AnsweringCode1
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought VerificationCode1
Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation CapabilitiesCode1
Do Language Models Understand Time?Code1
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language ModelsCode1
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at ScaleCode1
Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical FindingsCode1
Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual HallucinationCode1
Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical ReasoningCode1
DC3DO: Diffusion Classifier for 3D ObjectsCode1
LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language ModelsCode1
HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal ReasoningCode1
MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language ModelsCode1
CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal ModelsCode1
Exploring the Transferability of Visual Prompting for Multimodal Large Language ModelsCode1
A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal ReasoningCode1
All in an Aggregated Image for In-Image LearningCode1
Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial ImageCode1
Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language ModelsCode1
Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency TrainingCode1
MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension TasksCode1
DOMINO: A Dual-System for Multi-step Visual Language ReasoningCode1
Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive FrameworkCode1
LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and GenerationCode1
Variational Causal Inference Network for Explanatory Visual Question AnsweringCode1
Show:102550
← PrevPage 4 of 13Next →
All datasetsREBUSMATH-VAlgoPuzzleVQA

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-4VAccuracy24—Unverified
2Gemini ProAccuracy13.2—Unverified
3LLaVa-1.5-13BAccuracy1.8—Unverified
4LLaVa-1.5-7BAccuracy1.5—Unverified
5BLIP2-FLAN-T5-XXLAccuracy0.9—Unverified
6QWENAccuracy0.9—Unverified
7CogVLMAccuracy0.9—Unverified
8InstructBLIPAccuracy0.6—Unverified
#ModelMetricClaimedVerifiedStatus
1GPT4VAccuracy22.76—Unverified
2Gemini ProAccuracy17.66—Unverified
3Qwen-VL-MaxAccuracy15.59—Unverified
4InternLM-XComposer2-VLAccuracy14.54—Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4Acc30.3—Unverified