Newest papers

Training-free Acceleration for Blind Compressed Image Restoration via Activation-Calibrated Singular Value Decomposition

Suhang Yao, Xin Li, Xijun Wang, Yufei Wang, Yeying Jin, Zhibo Chen · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29959 · open-access PDF

German

Transformer-basierte Modelle erzielen bei blinder komprimierter Bildwiederherstellung (CIR) unter unbekannten Kompressionseinstellungen eine starke Leistung, aber ihre dicht gestapelten Projektionsoperatoren machen die Bereitstellung kostspielig. Wir untersuchen die schulungsfreie Beschleunigung solcher Modelle durch eine empirische, operator-Ebene-Analyse. Insbesondere profilieren wir, wo die Berechnung konzentriert ist, charakterisieren Kanal-ähnliche Aktivierungsverteilungen unter komprimierten Eingängen und untersuchen den Einzelwertverfall repräsentativer Projektionsgewichte.

Machine translation (Meta M2M100); the English original follows.

Abstract

Transformer-based models achieve strong performance on blind compressed image restoration (CIR) under unknown compression settings, but their densely stacked projection operators make deployment costly. We study training-free acceleration for such models through an empirical, operator-level analysis. Specifically, we profile where computation is concentrated, characterize channel-wise activation distributions under compressed inputs, and examine the singular-value decay of representative projection weights. These measurements identify the recurring projections in the attention, feed-forward, c

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29959, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange