← 記事一覧に戻る
E²-CRF method accelerates frequency domain diffusion models for time series generation with ~2.2 speedup
arXiv cs.LG · 2026年4月28日
AI要約
- •Researchers propose E²-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching), a technique that speeds up diffusion models (AI systems that generate time series data through iterative refinement) by exploiting spectral localization and mirror symmetry in frequency domain signals.
- •The method uses a closed-loop error-feedback system to adaptively cache transformer KV features across diffusion steps, triggering recomputation only when needed via event-driven residual dynamics rather than fixed schedules, selectively recomputing high-energy or rapidly-changing tokens while reusing cached features for stable components.
- •E²-CRF achieves ~2.2 speedup while maintaining sample quality and was validated on 5 datasets; code is available online and integrated into an existing repository.
関連記事
大規模言語モデル
Atlassian expands Google Cloud partnership in April 2026, integrating Gemini 3 Flash models and Google Workspace into Rovo AI platform.
Yahoo Finance AI·2026年4月28日
大規模言語モデル
OpenAI loosens Microsoft exclusivity to distribute via Google TPU and AWS; Xiaomi open-sources MiMo-V2.5 with 1M-token context; Sakana's 7B Conductor orchestrates frontier models to reach 83.9% on LiveCodeBench.
Latent Space·2026年4月28日
大規模言語モデル
Article body unavailable — unable to generate summary
Hacker News·2026年4月28日
大規模言語モデル
QuickDef, an AI-powered dictionary extension, launches to help English learners understand words in PDFs and web pages by double-clicking
Hacker News·2026年4月28日
大規模言語モデル
AI agents' task complexity is doubling every 4 months, with time horizons growing exponentially from 30 seconds in 2022 to 14+ hours today
Hacker News·2026年4月28日
AIニュースを毎日お届け
200以上のソースから厳選したAIニュースを毎日無料でお届けします。
無料で始める