<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Model Evaluation on C.CUI's Log</title><link>https://cuicaihao.github.io/tags/model-evaluation/</link><description>Recent content in Model Evaluation on C.CUI's Log</description><generator>Hugo</generator><language>en-AU</language><lastBuildDate>Sat, 14 Nov 2026 07:00:00 +1100</lastBuildDate><atom:link href="https://cuicaihao.github.io/tags/model-evaluation/index.xml" rel="self" type="application/rss+xml"/><item><title>Misreading Charts: How Correct Numbers Lead to Wrong Decisions in Machine Learning</title><link>https://cuicaihao.github.io/posts/2026-11-14-model-comparison-visualizationzh/</link><pubDate>Sat, 14 Nov 2026 07:00:00 +1100</pubDate><guid>https://cuicaihao.github.io/posts/2026-11-14-model-comparison-visualizationzh/</guid><description>A chart can be numerically correct and still support the wrong decision. The failure often lies not in the arithmetic, but in a mismatch between the evaluation boundary, the meaning of the output, and the decision the chart is expected to support. Six examples show what overview charts leave out and which diagnostic evidence should accompany them.</description></item><item><title>Time Series Foundation Models - Google TimesFM (Part 1): Model, Algorithms, and Engineering Practice</title><link>https://cuicaihao.github.io/posts/2026-11-07-dissecting-google-timesfm-architecture-and-algorithms/</link><pubDate>Sat, 07 Nov 2026 10:30:00 +1100</pubDate><guid>https://cuicaihao.github.io/posts/2026-11-07-dissecting-google-timesfm-architecture-and-algorithms/</guid><description>Benchmark leaderboards list dozens of time-series foundation models, but production selection requires more than an average rank. This article dissects Google TimesFM from version 1.0 to 3.0: input patching and local instance normalization remain consistent, while decoding shifts from a 128-step output head to 3.0&amp;rsquo;s parallel CPM filling, covariate handling evolves from external XReg linear regression to native multivariate attention, and open checkpoints split into commercial and non-commercial tracks.</description></item><item><title>Should We Build a Foundation Model in a Forest of Trees? A Pragmatic Guide to Time Series Foundation Models</title><link>https://cuicaihao.github.io/posts/2026-11-01-time-series-foundation-models-vs-gbdt-practical-guide/</link><pubDate>Sun, 01 Nov 2026 07:00:00 +1100</pubDate><guid>https://cuicaihao.github.io/posts/2026-11-01-time-series-foundation-models-vs-gbdt-practical-guide/</guid><description>&amp;lsquo;Foundation models for time series&amp;rsquo; actually encompasses two fundamentally different approaches: repurposing pretrained language models via adaptation layers (where ablations reveal removing the LLM leaves accuracy unchanged while speeding up training by orders of magnitude), and native time series foundation models pretrained from scratch on physical temporal data (which demonstrate real promise in cold-start and covariate-driven forecasting). Here is an engineering reality check and practical decision guide.</description></item></channel></rss>