Papers with Code 아카이브
MME
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
VideoDeepResearch: Long Video Understanding With Agentic Tool Using
Language-Vision Planner and Executor for Text-to-Visual Reasoning
DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering
SiLVR: A Simple Language-based Video Reasoning Framework
EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models
VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation
Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization
Visual Instruction Tuning with Chain of Region-of-Interest
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
Improving LLM Video Understanding with 16 Frames Per Second
Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
Re-Imagining Multimodal Instruction Tuning: A Representation View
Ultra-High-Frequency Harmony: mmWave Radar and Event Camera Orchestrate Accurate Drone Landing
Towards Text-Image Interleaved Retrieval
AIDE: Agentically Improve Visual Language Model with Domain Experts
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding
MME-Industry: A Cross-Industry Multimodal Evaluation Benchmark
Temporal Preference Optimization for Long-Form Video Understanding
Expand VSR Benchmark for VLLM to Expertize in Spatial Rules
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.