A Smaller Transformer in Your Transformer

arXiv:2609.20100 · cs.CV · Submitted 2026-09-17 · Read on arXiv

cs.CV

Submitted: 2026-09-17

Updated: 2026-09-17

Code: https://github.com/dsb-ifi/TWT

Terminology

• Transformer — 75× in this paper · explained in 2 episodes
• Redundancy — 23× in this paper · explained in 2 episodes
• Distillation — 16× in this paper · explained in 2 episodes
• Pruning — 14× in this paper · explained in 4 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Intrinsic Dimension — 8× in this paper · explained in 2 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Feature Extraction — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Homogeneity — 2× in this paper · explained in 2 episodes
• Whole-Slide Image — 2× in this paper
• Ablation study — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• SGDR: Stochastic Gradient Descent with Warm Restarts
• Hibou: A Family of Foundational Vision Transformers for Pathology
• DINOv3

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models