SOTAVerified

Multimodal Reasoning

Reasoning over multimodal inputs.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 176–200 of 302 papers

TitleStatusHype
Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration—0
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking—0
Position: Empowering Time Series Reasoning with Multimodal LLMs—0
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal PuzzlesCode2
Efficient Reasoning with Hidden ThinkingCode2
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark—0
DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests—0
Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the WildCode0
EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models—0
LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question AnsweringCode0
Diving into Self-Evolving Training for Multimodal Reasoning—0
SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object LocalizationCode0
Progressive Multimodal Reasoning via Active Retrieval—0
FiVL: A Framework for Improved Vision-Language AlignmentCode0
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence—0
Do Language Models Understand Time?Code1
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language ModelsCode1
A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges—0
Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes—0
Optimizing Vision-Language Interactions Through Decoder-Only Models—0
EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing—0
Neptune: The Long Orbit to Benchmarking Long Video UnderstandingCode2
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at ScaleCode1
Aguvis: Unified Pure Vision Agents for Autonomous GUI InteractionCode3
Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical FindingsCode1
Show:102550
← PrevPage 8 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