Should We Skip Diffusion?
cs.LG, cs.CV
Submitted: 2026-10-04
Updated: 2026-10-04
Sources
- The Quantization Benefits of Residual-Free Transformers
- Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping
- SPair-71k: A Large-scale Benchmark for Semantic Correspondence
- Localizing Objects with Self-Supervised Transformers and no Labels
- Conditioning Residuals for Diffusion Models via Representation Feedback
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks