SOTAVerified

MME

MME is a comprehensive evaluation benchmark for multimodal large language models. It measures both perception and cognition abilities on a total of 14 subtasks, including existence, count, position, color, poster, celebrity, scene, landmark, artwork, OCR, commonsense reasoning, numerical calculation, text translation, and code reasoning.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–60 of 95 papers

TitleStatusHype
Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding—0
Re-Imagining Multimodal Instruction Tuning: A Representation ViewCode0
Ultra-High-Frequency Harmony: mmWave Radar and Event Camera Orchestrate Accurate Drone Landing—0
AIDE: Agentically Improve Visual Language Model with Domain Experts—0
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency—0
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment—0
Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding—0
MME-Industry: A Cross-Industry Multimodal Evaluation Benchmark—0
Temporal Preference Optimization for Long-Form Video Understanding—0
Expand VSR Benchmark for VLLM to Expertize in Spatial RulesCode0
Show:102550
← PrevPage 6 of 10Next →

No leaderboard results yet.