Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 6 figures, 5 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation
- Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
- FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- Progressive Distillation for Fast Sampling of Diffusion Models
- FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
- Denoising Diffusion Implicit Models
- PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores
- PEAR: Pixel-aligned Expressive humAn mesh Recovery
- Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
- Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models
- Accelerating Diffusion Transformers with Token-wise Feature Caching
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