Research map / Architectures and efficiency / Attention and transformers
White-Box Transformers via Sparse Rate Reduction
Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Benjamin David Haeffele, Yi Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| scale CRATE from Tiny to Large | CRATE · ImageNet-1K | top-1 accuracy (%): 66.7 -> 71.3 | Improved |
| use white-box CRATE-Base instead of ViT-Small at similar parameter count | transformer architecture · ImageNet-1K | top-1 accuracy (%): 72.4 -> 70.8 | Hurt |
| CRATE-Large vs ViT-Small on CIFAR100 transfer | transfer fine-tuning · CIFAR100 | top-1 accuracy (%): 83.2 -> 83.6 | No clear effect |
| CRATE vs ViT on Oxford-IIIT-Pets transfer | transfer fine-tuning · Oxford-IIIT-Pets | top-1 accuracy (%): 88.6 -> 87.4 | Hurt |
| train CRATE (learn subspaces and dictionaries) versus untrained (ablation) | CRATE-Base · ImageNet-1K layer-wise analysis | compression and sparsity objective improvement across layers | Improved |
Closest papers by meaning
- Attention-Only Transformers via Unrolled Subspace Denoising (ICML 2025 · similarity 0.88)
- Masked Completion via Structured Diffusion with White-Box Transformers (ICLR 2024 · similarity 0.88)
- Scaling White-Box Transformers for Vision (NeurIPS 2024 · similarity 0.87)
- An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models (NeurIPS 2024 · similarity 0.87)
- Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction (ICLR 2025 · similarity 0.85)
- A Global Geometric Analysis of Maximal Coding Rate Reduction (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
