arxiv
PublishedMay 27, 2026 at 4:00 AM
Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2
Publisher summary· verbatim
arXiv:2605.26628v1 Announce Type: new Abstract: This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public ViDiT-Q post-training quantization pipeline to Wan2.2 under the HiFloat4 numerical format. We quantiz
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning38marxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning38marxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models38marxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents38mThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗