HackerTrans
トップ新着トレンドコメント過去質問紹介求人

waldarbeiter

no profile record

投稿

PyTorch Geometric

pytorch-geometric.readthedocs.io
1 ポイント·投稿者 waldarbeiter·5 か月前·0 コメント

1000 Layer Networks for Self-Supervised RL (NeurIPS 2025 Best Paper Award)

arxiv.org
2 ポイント·投稿者 waldarbeiter·6 か月前·0 コメント

Logical Foundations of Cyber-Physical Systems (Winter 2025)

symbolaris.com
1 ポイント·投稿者 waldarbeiter·6 か月前·0 コメント

Compiler Design (Summer 2025)

symbolaris.com
1 ポイント·投稿者 waldarbeiter·7 か月前·0 コメント

Workings of Science: Debunked Software Theories (2022) [pdf]

dl.acm.org
17 ポイント·投稿者 waldarbeiter·10 か月前·2 コメント

コメント

waldarbeiter
·8 日前·議論
[dead]
waldarbeiter
·4 か月前·議論
There is actually a whole lot of research around the "use less data" called data pruning. The goal in a lot of cases there is basically to achieve the same performance with less data. For example [1] received quite some attention in the past.

[1] https://arxiv.org/abs/2206.14486
waldarbeiter
·5 か月前·議論
Is the 1 cm spec 1σ (or less) or worst-case? It’s a safety-critical application.
waldarbeiter
·5 か月前·議論
There seems to be a moat like infrastructure/gpus and talent. The best models right now come from companies with considerable resources/funding.
waldarbeiter
·5 か月前·議論
That was not mar a Lago but in New Jersey
waldarbeiter
·6 か月前·議論
My website of choice whenever I have to deal with references is dblp [1]. In my opinion more reliable than Google scholar in creating correct BibTeX. Also when searching for a paper you clearly see where it has been published or if it is only on arxiv.

[1] https://dblp.org/
waldarbeiter
·6 か月前·議論
"4,000 tons is almost four million kilograms"
waldarbeiter
·6 か月前·議論
What does "wolf in sheep's clothing" mean for you, concretely, outside of metaphors?
waldarbeiter
·10 か月前·議論
by Walter Tichy
waldarbeiter
·10 か月前·議論
The different JDK builds are almost all built from OpenJDK. Maven and Gradle cover nearly all use cases. The complexity is not that high.
waldarbeiter
·10 か月前·議論
If it would be easy there would already be a car costing a few million that few can afford but that has solved AD. But there isn't.