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 1–50 of 95 papers

TitleStatusHype
VideoEval-Pro: Robust and Realistic Long Video Understanding EvaluationCode4
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language ModelsCode4
Long Context Transfer from Language to VisionCode4
Flash-VStream: Efficient Real-Time Understanding for Long Video StreamsCode3
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming VideosCode3
Lyra: An Efficient and Speech-Centric Framework for Omni-CognitionCode3
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMsCode3
Video-RAG: Visually-aligned Retrieval-Augmented Long Video ComprehensionCode3
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement LearningCode2
VideoDeepResearch: Long Video Understanding With Agentic Tool UsingCode2
SpaceR: Reinforcing MLLMs in Video Spatial ReasoningCode2
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video ComprehensionCode2
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention CausalityCode2
L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object DetectionCode2
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long VideosCode2
Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive DecodingCode2
Honeybee: Locality-enhanced Projector for Multimodal LLMCode2
MMICL: Empowering Vision-language Model with Multi-Modal In-Context LearningCode2
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual QuestionsCode2
Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative InstructionsCode2
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language ModelsCode2
SiLVR: A Simple Language-based Video Reasoning FrameworkCode1
FRAG: Frame Selection Augmented Generation for Long Video and Long Document UnderstandingCode1
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video UnderstandingCode1
Towards Text-Image Interleaved RetrievalCode1
Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language BootstrappingCode1
To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language ModelsCode1
ParGo: Bridging Vision-Language with Partial and Global ViewsCode1
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video AnalysisCode1
Pensieve: Retrospect-then-Compare Mitigates Visual HallucinationCode1
HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language ModelsCode1
Prompt Highlighter: Interactive Control for Multi-Modal LLMsCode1
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference OptimizationCode1
What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction TuningCode1
Masked Motion Encoding for Self-Supervised Video Representation LearningCode1
Semi-supervised Domain Adaptation via Minimax EntropyCode1
Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs—0
Language-Vision Planner and Executor for Text-to-Visual Reasoning—0
DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding—0
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering—0
EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models—0
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs—0
Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models—0
Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models—0
VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization—0
Visual Instruction Tuning with Chain of Region-of-Interest—0
An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes—0
MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models—0
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language ModelsCode0
Improving LLM Video Understanding with 16 Frames Per Second—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.