Shiva-DiT: Residual-Based Differentiable Top- k Selection for Efficient Diffusion Transformers
cs.LG, cs.AI, cs.CV
Submitted: 2026-02-05
Updated: 2026-09-02
Comments: 37 pages
Code: https://github.com/huggingface/peft
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
- Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
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