SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.03057 · 2026

TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models

Yiran Chen, Huanrui Yang, Jong Ko, Jinhee Kim, Dongwei Wang, Jeon, Seokho Han, Eun Kang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Static quantization assigns one weight precision to every denoising step. To preserve quality, that precision must accommodate the most quantization-sensitive step, even though many other steps can tolerate fewer bits. The resulting model may satisfy its memory budget, but it repeatedly pays worstcase arithmetic throughout the denoising trajectory. We introduce Temporal-Adaptive Bit Sparsification Quantization (TASQ) to separate these two costs. TASQ stores one shared maximum-precision weight buffer and learns a Temporal-Spatial LSB Mask that selects a lower effective precision for each layer and denoising stage by truncating least-significant bits. Storage therefore remains fixed by the worst case, while BitOPs decrease at less sensitive stages without per-stage weight copies or runtime search. A Temporal-Precision Engine maps the learned schedule to bit-serial execution, where cycles scale with effective precision and switching precision has no measured cycle overhead. On PixArt-Σ, SANA-1.6B, and SDXL-Turbo, TASQ achieves quality comparable to static quantization with less computation. Together with the Temporal-Precision Engine, it reduces execution cycles by 25-50% over static quantization and by 6.1-7.5× over a naive static 8-bit bit-serial execution. Code is available at https://github.com/seokho-han/tasq.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2608.03057")
get_code_for_paper("2608.03057")
have("2608.03057")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2608.03057.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2608.03057.svg)](https://syntology.ai/paper/2608.03057)

Connect an agent — have() is free.