SpecKCast: frequency-domain Kalman forecasting accelerates diffusion transformers training-free
SamsungResearch · hf · 2026-10-21
Researchers from the University of Toronto, Vector Institute, and Samsung AI Center–Toronto propose SpecKCast, a training-free method to accelerate Diffusion Transformer inference.
- Motivation: prior caching/forecasting methods extrapolate all frequency components uniformly, ignoring that spatial-frequency bands evolve at different rates across denoising stages, so errors amplify as more steps are skipped
- Method: apply a 2D DCT to the output, track each frequency band with a lightweight Kalman filter along a band-specific non-uniform time coordinate, plus adaptive step scheduling
- Result: faster image and video generation with minimal memory overhead
A practical acceleration recipe for teams optimizing diffusion inference.
More from Research
- EvoMusArt 2027 opens submissions, due Nov 1, 2026 in Mainz, Germany — evomusart_conference · 2026-10-21
- AI denoising recovers superconductor spectra in 12s vs 5h, with error bars on the result — bravo_abad · 2026-10-21
- LLM2R recasts 3D part assembly as sequence modeling with a decoder-only LLM — NationalUniversityofSingapore · 2026-10-21
- Ant International's FlowState treats execution state as memory for long-horizon LLM agents — ant-intl · 2026-10-21
- Google's TEAL evolves reusable analytics tools for coding agents without ground-truth labels — google · 2026-10-21
- Tencent's ASAP evaluates agentic capabilities in pretrained base models before post-training — tencent · 2026-10-21