conftrace_

token fusion

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

vision transformer (4) image classification (3) feature squeezing (1) one-step-ahead attention (1) self-attention optimization (1) vision transformer efficiency (1) lid ar (1) representation privacy (1) images (1) large language model (1)

Papers

How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation ICML 2025 Mimir: Improving Video Diffusion Models for Precise Text Understanding CVPR 2025 Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers CVPR 2024 Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers CVPR 2023 GuideFormer: Transformers for Image Guided Depth Completion CVPR 2022 Multimodal Token Fusion for Vision Transformers CVPR 2022 TextFusion: Privacy-Preserving Pre-trained Model Inference via Token Fusion EMNLP 2022 CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification ICCV 2021