Token Reduction
26 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Token Reduction
Most implemented papers
TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference
To address this issue, we propose a dynamic token reduction approach to accelerate PLMs' inference, named TR-BERT, which could flexibly adapt the layer number of each token in inference to avoid redundant calculation.
AdaViT: Adaptive Tokens for Efficient Vision Transformer
A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
PuMer: Pruning and Merging Tokens for Efficient Vision Language Models
csarron/pumer
•
•
Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image.
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers
tue-mps/cts-segmenter
•
•
CVPR 2023
This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs).
Which Tokens to Use? Investigating Token Reduction in Vision Transformers
JoakimHaurum/TokenReduction
•
•
While different methods have been explored to achieve this goal, we still lack understanding of the resulting reduction patterns and how those patterns differ across token reduction methods and datasets.
HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition
Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT).
LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
In response, we propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs.
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
alinlab/homer
•
•
Large language models (LLMs) have shown remarkable performance in various natural language processing tasks.
ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
tue-mps/algm-segmenter
•
•
CVPR 2024
This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers.
Bridging Local Details and Global Context in Text-Attributed Graphs
Representation learning on text-attributed graphs (TAGs) is vital for real-world applications, as they combine semantic textual and contextual structural information.
