llm-catalog-archive

Change

db364ab

db364ab25155aed5c73d76feef47bf635bc94276 · commit on GitHub

huggingface-blog-feed: changed (264634 bytes, HTTP 200)

raw/huggingface-blog-feed/response.xml modified

Lines added
+24
Lines removed
-12
Stored bytes at this commit
264,634
Timestamp
observed
Raw artifact at this commit
raw/huggingface-blog-feed/response.xml
Recorded headers
observed_at2026-11-04T06:21:59.571Z
origin_datenull
status200
final URLhttps://huggingface.co/blog/feed.xml
etagW/"409ba-TNjiov8iSZw8bjH/Au21MeF/0Fg"
last-modifiednull
dateWed, 04 Nov 2026 06:21:59 GMT
agenull
cache-controlnull
cf-cache-statusnull
content-encodinggzip
content-lengthnull
@@@ -6,6 +6,30 @@
<link>https://huggingface.co/blog</link>
<description>The Hugging Face blog</description>
<language>en-US</language>
+ <item>
+ <title>StateBench: Testing how language models track state changes over long documents</title>
+ <pubDate>Tue, 03 Nov 2026 17:15:21 GMT</pubDate>
+ <link>https://huggingface.co/blog/allenai/statebench</link>
+ <guid isPermaLink="false">https://huggingface.co/blog/allenai/statebench</guid>
+ </item>
+ <item>
+ <title>Palette: teaching a small model to build decks in your design language</title>
+ <pubDate>Tue, 03 Nov 2026 16:35:36 GMT</pubDate>
+ <link>https://huggingface.co/blog/ibm-research/palette-deck-building</link>
+ <guid isPermaLink="false">https://huggingface.co/blog/ibm-research/palette-deck-building</guid>
+ </item>
+ <item>
+ <title>CWE-bench v2: More coverage, quality, and transparency</title>
+ <pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate>
+ <link>https://huggingface.co/blog/cwe-bench</link>
+ <guid isPermaLink="true">https://huggingface.co/blog/cwe-bench</guid>
+ </item>
+ <item>
+ <title>Transformers Model Integration Contracts</title>
+ <pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate>
+ <link>https://huggingface.co/blog/transformers-mic</link>
+ <guid isPermaLink="true">https://huggingface.co/blog/transformers-mic</guid>
+ </item>
<item>
<title>nemotron-halloween</title>
<pubDate>Fri, 30 Oct 2026 17:57:24 GMT</pubDate>
@@@ -42,12 +66,6 @@
<link>https://huggingface.co/blog/LiquidAI/lfm3</link>
<guid isPermaLink="false">https://huggingface.co/blog/LiquidAI/lfm3</guid>
</item>
- <item>
- <title>Can we trust LLMs to judge whether a research idea is novel?</title>
- <pubDate>Tue, 27 Oct 2026 16:12:42 GMT</pubDate>
- <link>https://huggingface.co/blog/allenai/novelty-bench</link>
- <guid isPermaLink="false">https://huggingface.co/blog/allenai/novelty-bench</guid>
- </item>
<item>
<title>Does Your Model Run on AWS Trainium? Look It Up</title>
<pubDate>Fri, 23 Oct 2026 00:00:00 GMT</pubDate>
@@@ -60,12 +78,6 @@
<link>https://huggingface.co/blog/microsoft/thinkingbox-training</link>
<guid isPermaLink="false">https://huggingface.co/blog/microsoft/thinkingbox-training</guid>
</item>
- <item>
- <title>Ensemble forecasting with IBM Granite time-series models</title>
- <pubDate>Thu, 22 Oct 2026 07:51:31 GMT</pubDate>
- <link>https://huggingface.co/blog/ibm-research/granite-timeseries-ensemble-r1</link>
- <guid isPermaLink="false">https://huggingface.co/blog/ibm-research/granite-timeseries-ensemble-r1</guid>
- </item>
<item>
<title>How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications</title>
<pubDate>Wed, 21 Oct 2026 17:35:36 GMT</pubDate>