机房的电力架构：UPS、柴发与双路供电
数据中心的可靠性是从供电架构里长出来的：本文拆解从市电引入到机架 PDU 的供电链条，讲清 UPS、柴油发电机与双路供电各自的职责边界，以及 Tier 分级背后的可靠性逻辑。
阅读全文 →
全部文章
ARCHIVE 共 1876 条AI 降低了创造的门槛，B 站则想放大创造的回声
震撼其他人的 AI 创造，必须先震撼自己 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes
Video foundation models increasingly rely on large-scale pretraining data, yet the end-to-end data pipelines behind them…
OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution
Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back i…
TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation
Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, und…
Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation
Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across sh…
Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning
Training strategy, namely whether to retrain from scratch or fine-tune from the previous checkpoint, is an overlooked de…
Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model
We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series found…
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly …
DriveZero: End-to-End Driving Beyond Human Demonstrations
Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constra…
Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models
Large language models used for code editing can be trained and deployed in at least two output regimes: direct generatio…
Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts
We present Srijika, a system for producing installable OpenType fonts for nine Brahmic scripts: Devanagari, Tamil, Benga…
WorldSculpt: Generating Compositional Worlds from Grounded Videos
We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects…