STORM is a training-free spatial-aware token reduction framework that reformulates compression on spatial units to preserve grid topology and neighborhood coherence in visual state space models.
International Conference on Learning Representations , month =
4 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
4
Pith papers citing it
20
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
citing papers explorer
-
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
STORM is a training-free spatial-aware token reduction framework that reformulates compression on spatial units to preserve grid topology and neighborhood coherence in visual state space models.
-
Towards Understanding Self-Pretraining for Sequence Classification
Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.
-
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.