SOTAVerified

Multimodal Reasoning

Reasoning over multimodal inputs.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 302 papers

TitleStatusHype
SToLa: Self-Adaptive Touch-Language Framework with Tactile Commonsense Reasoning in Open-Ended Scenarios—0
X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains—0
Advancing Conversational Diagnostic AI with Multimodal Reasoning—0
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation—0
Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models—0
MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind—0
VideoMultiAgents: A Multi-Agent Framework for Video Question AnsweringCode1
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for ReasoningCode7
VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization—0
GeoSense: Evaluating Identification and Application of Geometric Principles in Multimodal Reasoning—0
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement LearningCode2
Structured Graph Representations for Visual Narrative Reasoning: A Hierarchical Framework for Comics—0
SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model—0
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge—0
Breaking the Data Barrier -- Building GUI Agents Through Task GeneralizationCode1
Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation—0
HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented GenerationCode2
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding—0
VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering—0
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement LearningCode2
Kimi-VL Technical ReportCode5
MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language ModelsCode1
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-ThoughtCode7
MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models—0
Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)—0
Show:102550
← PrevPage 5 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