DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

arXiv:2606.15796 · cs.CV, cs.AI · Submitted 2026-06-14 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-06-14

Updated: 2026-10-26

Terminology

• Transformer — 3× in this paper · explained in 2 episodes
• Transformers — 3× in this paper · explained in 2 episodes
• Attention Maps — 1× in this paper · explained in 2 episodes
• Faithfulness — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Mechanistic Interpretability — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes

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