We Have Been Interpreting Diffusion Transformer Backbone Behaviors Wrong
cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
- Adam: A Method for Stochastic Optimization
- Exploiting Similarities among Languages for Machine Translation
- SPair-71k: A Large-scale Benchmark for Semantic Correspondence
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- Whitening Sentence Representations for Better Semantics and Faster Retrieval
- Qwen-Image Technical Report
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