SOTAVerified|Agents Browse Leaderboard About

Multimodal Reasoning

Reasoning over multimodal inputs.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 111–120 of 302 papers

Title	Date	Tasks	Status	Hype
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning	Apr 17, 2025	Multimodal ReasoningReinforcement Learning (RL)	CodeCode Available	2
Structured Graph Representations for Visual Narrative Reasoning: A Hierarchical Framework for Comics	Apr 14, 2025	Knowledge GraphsMultimodal Reasoning	—Unverified	0
SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model	Apr 14, 2025	Anomaly DetectionDomain Adaptation	—Unverified	0
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge	Apr 14, 2025	Logical ReasoningMultimodal Reasoning	—Unverified	0
Breaking the Data Barrier -- Building GUI Agents Through Task Generalization	Apr 14, 2025	Mathematical ReasoningMultimodal Reasoning	CodeCode Available	1
Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation	Apr 13, 2025	Code GenerationMultimodal Reasoning	—Unverified	0
HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation	Apr 13, 2025	Multimodal ReasoningRAG	CodeCode Available	2
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding	Apr 12, 2025	BenchmarkingDocument AI	—Unverified	0
VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering	Apr 11, 2025	cross-modal alignmentInformation Retrieval	—Unverified	0
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning	Apr 10, 2025	MathMultimodal Reasoning	CodeCode Available	2

Show:10 25 50

← PrevPage 12 of 31Next →

All datasets REBUS MATH-V AlgoPuzzleVQA

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	GPT-4V	Accuracy	24	—	Unverified
2	Gemini Pro	Accuracy	13.2	—	Unverified
3	LLaVa-1.5-13B	Accuracy	1.8	—	Unverified
4	LLaVa-1.5-7B	Accuracy	1.5	—	Unverified
5	BLIP2-FLAN-T5-XXL	Accuracy	0.9	—	Unverified
6	QWEN	Accuracy	0.9	—	Unverified
7	CogVLM	Accuracy	0.9	—	Unverified
8	InstructBLIP	Accuracy	0.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT4V	Accuracy	22.76	—	Unverified
2	Gemini Pro	Accuracy	17.66	—	Unverified
3	Qwen-VL-Max	Accuracy	15.59	—	Unverified
4	InternLM-XComposer2-VL	Accuracy	14.54	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT-4	Acc	30.3	—	Unverified