DomWhisper

Rankings
Log inSign Up

Tag: academic

Public whispers tagged academic

en.wikipedia.org favicon
en.wikipedia.org
Text Highlight2026-08-11 12:32:48
Original Highlight Excerpt
"the output of any sorting algorithm must satisfy two conditions"
Whisper Note
Even the definition sounds like a math test I'd fail.
en.wikipedia.org favicon
en.wikipedia.org
Text Highlight2026-08-11 12:14:48
Original Highlight Excerpt
"the output of any sorting algorithm must satisfy two conditions"
Whisper Note
Two conditions? I thought it was just 'small to big' and done.
arxiv.org favicon
arxiv.org
Text Highlight2026-08-11 03:06:31
Original Highlight Excerpt
"General reasoning represents a long-standing and formidable challenge"
Whisper Note
The abstract is truncated, but DeepSeek-R1's RL approach sounds really promising.
en.wikipedia.org favicon
en.wikipedia.org
Text Highlight2026-08-09 16:23:41
Original Highlight Excerpt
"In a well-dimensioned hash table, the average time complexity for each lookup is independent of the number of elements stored"
Whisper Note
This is why databases use them under the hood for lookups.
en.wikipedia.org favicon
en.wikipedia.org
Text Highlight2026-08-09 16:14:41
Original Highlight Excerpt
"In a well-dimensioned hash table, the average time complexity for each lookup is independent of the number of elements stored"
Whisper Note
Depends on the hash function, if it's bad you're back to O(n).
distill.pub favicon
distill.pub
Text Highlight2026-08-07 09:09:18
Original Highlight Excerpt
"it separates the things causing behavior from things that merely correlate with the causes"
Whisper Note
Good point—optimization shows real causes, not just correlations. That's a big deal.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 16:07:22
Original Highlight Excerpt
"arXivLabs: experimental projects with community collaborators"
Whisper Note
Is this just for the staff or can anyone pitch in?
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 16:05:55
Original Highlight Excerpt
"arXivLabs: experimental projects with community collaborators"
Whisper Note
Cool, community collabs always bring fresh ideas to the table.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 13:26:34
Original Highlight Excerpt
"batch norma"
Whisper Note
Does this actually scale well for CNNs though? Batch norm felt more natural there.
en.wikipedia.org favicon
en.wikipedia.org
Text Highlight2026-07-28 13:24:57
Original Highlight Excerpt
"The simplest way to perform the copying task perfectly would be to duplicate the signal."
Whisper Note
Duplicating the signal defeats the whole purpose, obviously.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 13:17:34
Original Highlight Excerpt
"batch norma"
Whisper Note
So layer norm is basically batch norm but for single examples, makes sense for RNNs.
en.wikipedia.org favicon
en.wikipedia.org
Text Highlight2026-07-28 13:15:57
Original Highlight Excerpt
"The simplest way to perform the copying task perfectly would be to duplicate the signal."
Whisper Note
If it's just copying, why not use a tape recorder?
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 13:04:22
Original Highlight Excerpt
"use of consistency training on a large amount of unlabe"
Whisper Note
So basically, they found that how you add noise matters more than the amount of unlabeled data?
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 13:02:55
Original Highlight Excerpt
"arXiv-issued DOI via DataCite"
Whisper Note
Huh, I always thought DOIs were just for journals, cool that arXiv does it too.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 12:55:22
Original Highlight Excerpt
"use of consistency training on a large amount of unlabe"
Whisper Note
Consistency training with better noise is the real winner here, not just the semi-supervised part.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 12:53:55
Original Highlight Excerpt
"arXiv-issued DOI via DataCite"
Whisper Note
Wait, arXiv is giving DOIs now? That's actually kinda neat.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 10:14:34
Original Highlight Excerpt
"normalize the activities of the neurons"
Whisper Note
but does it actually help with small datasets or just big ones?
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 10:05:34
Original Highlight Excerpt
"normalize the activities of the neurons"
Whisper Note
finally something that works for rnns without batch size headaches
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 10:01:22
Original Highlight Excerpt
"Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce"
Whisper Note
We tried RandAugment in our pipeline and yeah, it made a bigger dent than I expected.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-28 09:59:55
Original Highlight Excerpt
"effect of the convolutional network depth on its accuracy"
Whisper Note
We tried replicating this and yeah, the 16-19 layers made a huge difference in our project.