SOTAVerified

Multimodal Reasoning

Reasoning over multimodal inputs.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 302 papers

TitleStatusHype
VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL—0
MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence CalibrationCode0
Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought—0
Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models—0
Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios—0
GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning—0
Advancing Multimodal Reasoning via Reinforcement Learning with Cold StartCode1
SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning—0
OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning—0
VidText: Towards Comprehensive Evaluation for Video Text UnderstandingCode1
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?Code2
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs—0
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning—0
Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning—0
Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval—0
Visual Abstract Thinking Empowers Multimodal ReasoningCode1
Agentic 3D Scene Generation with Spatially Contextualized VLMs—0
VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool UseCode2
SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable RewardsCode1
ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning—0
Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation—0
ChartGalaxy: A Dataset for Infographic Chart Understanding and GenerationCode3
MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation—0
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models—0
EVADE: Multimodal Benchmark for Evasive Content Detection in E-Commerce Applications—0
ARB: A Comprehensive Arabic Multimodal Reasoning BenchmarkCode1
Training-Free Reasoning and Reflection in MLLMs—0
Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL—0
LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language ModelsCode0
MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models—0
Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General ReasoningCode2
Emerging Properties in Unified Multimodal PretrainingCode9
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement LearningCode5
SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio InformationCode1
Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation—0
AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning—0
Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning—0
MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level SupervisionCode4
KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News DetectionCode0
MMS-VPR: Multimodal Street-Level Visual Place Recognition Dataset and Benchmark—0
LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?Code1
PRS-Med: Position Reasoning Segmentation with Vision-Language Model in Medical Imaging—0
Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans—0
Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert ReasonerCode2
Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning—0
Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning—0
Seed1.5-VL Technical Report—0
Overview of the NLPCC 2025 Shared Task 4: Multi-modal, Multilingual, and Multi-hop Medical Instructional Video Question Answering Challenge—0
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning ModelsCode4
Q-Heart: ECG Question Answering via Knowledge-Informed Multimodal LLMs—0
Show:102550
← PrevPage 2 of 7Next →
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