Papers with Code 아카이브

Token Reduction

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/NUS-HPC-AI-Lab/R-MeeTo

공식 코드

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

https://github.com/Vision-CAIR/LongVU

공식 코드

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

https://github.com/alinlab/homer

공식 코드

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs

https://github.com/anakin-skywalker-joseph/folder

공식 코드

FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance

https://github.com/arkel23/clca

공식 코드

Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition

https://github.com/benbergner/cropr

공식 코드

Token Cropr: Faster ViTs for Quite a Few Tasks

https://github.com/ceezh/silvr

공식 코드

SiLVR: A Simple Language-based Video Reasoning Framework

https://github.com/csarron/pumer

공식 코드

PuMer: Pruning and Merging Tokens for Efficient Vision Language Models

https://github.com/dun-research/haltingvt

공식 코드

HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition

https://github.com/fanshuozeng/simignore

공식 코드

Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation

https://github.com/faustrazor/not-all-thinking-tokens

공식 코드

Not All Tokens Are What You Need In Thinking

https://github.com/freedomintelligence/trim

공식 코드

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs

https://github.com/jackyfl/wico

공식 코드

Window Token Concatenation for Efficient Visual Large Language Models

https://github.com/kyk120/fpet

공식 코드

Faster Parameter-Efficient Tuning with Token Redundancy Reduction

https://github.com/locuslab/llava-token-compression

공식 코드

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters

https://github.com/movinghoon/dtem

공식 코드

Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers

https://github.com/omidiu/ca_tome

공식 코드

Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model

https://github.com/orailix/pact

공식 코드

PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models

https://github.com/penghao-wu/proxyv

공식 코드

Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM

https://github.com/salesforceairesearch/gemfilter

공식 코드

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction

https://github.com/shilinyan99/crosslmm

공식 코드

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

https://github.com/thu-nics/framefusion

공식 코드

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models

https://github.com/thunlp/TR-BERT

공식 코드

TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference

https://github.com/tue-mps/algm-segmenter

공식 코드

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers

https://github.com/tue-mps/cts-segmenter

공식 코드

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers

https://github.com/tungchintao/flowcut

공식 코드

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

https://github.com/visionxlab/lrs-vqa

공식 코드

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

https://github.com/visresearch/LLaVA-STF

공식 코드

Learning Compact Vision Tokens for Efficient Large Multimodal Models

https://github.com/wuyushuwys/tor_ssm

공식 코드

Rethinking Token Reduction for State Space Models

https://github.com/wykk00/graphbridge

공식 코드

Bridging Local Details and Global Context in Text-Attributed Graphs

https://github.com/yichen14/fastadasp

공식 코드

FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model

https://github.com/zlkong/awesome-token-compression-reduction

공식 코드

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality

https://github.com/42Shawn/LLaVA-PruMerge

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models

https://github.com/JoakimHaurum/TokenReduction

Which Tokens to Use? Investigating Token Reduction in Vision Transformers

https://github.com/NVlabs/A-ViT

AdaViT: Adaptive Tokens for Efficient Vision Transformer

https://github.com/chendelong1999/subobjects

One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.