Skip to content
conftrace_

token sparsification

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

vision transformer (4) efficient computing (3) attention mechanism (2) object detection (2) event-based object detection (1) sparse mamba (1) dynamic token pruning (1) dual alignment (1) video-language pre-training (1) attention locality (1)

Papers

MedSpaformer: A Transferable Transformer with Multi-Granularity Token Sparsification for Medical Time Series Classification AAAI 2026 SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inference CVPR 2026 SMamba: Sparse Mamba for Event-based Object Detection AAAI 2025 VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification CVPR 2025 AdaFormer: Efficient Transformer with Adaptive Token Sparsification for Image Super-resolution AAAI 2024 DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms NeurIPS 2024 Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration ICML 2024 A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity ICLR 2023 Making Vision Transformers Efficient From a Token Sparsification View CVPR 2023 SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training ICCV 2023 DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification NeurIPS 2021