Papers with Code 아카이브
Token Reduction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers
SiLVR: A Simple Language-based Video Reasoning Framework
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
Not All Tokens Are What You Need In Thinking
Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality
Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning
CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM
DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method
DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
ZipR1: Reinforcing Token Sparsity in MLLMs
Dynamic Compressing Prompts for Efficient Inference of Large Language Models
PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models
Window Token Concatenation for Efficient Visual Large Language Models
Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning
Faster Parameter-Efficient Tuning with Token Redundancy Reduction
Token Dynamics: Towards Efficient and Dynamic Video Token Representation for Video Large Language Models
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study
BatchGEMBA: Token-Efficient Machine Translation Evaluation with Batched Prompting and Prompt Compression
Knowing When to Stop: Dynamic Context Cutoff for Large Language Models
MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
Learning Free Token Reduction for Multi-Modal Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.