Ah cool! Great to see accessibility stuff like this. Listening to papers makes it much easier for me to focus on the content.
I made my own little service that converts any webpage to hopefully the parsed content then uses Google TTS and then published it to a bucket and s3 feed and I listen to them on my phone before bed.
Nice idea - would love to have some kind of daily mix with all the papers from my field / some way to prioritise them automatically based on the most important ones I should have read
What do you think would be a good way to prioritise papers? It seems to be especially difficult when the papers are not yet rated by the users. We were thinking of some algorithm that would analyse the authors of the paper and their previous track record, but it feels somewhat unfair towards the new/young academics?
hmm that’s true - I think if you could get a measure of interest for the paper like views on arxiv or number of mentions online, that could be a good metric to use.
it’s also possible that the LLM will be able to determine well which results are important vs which are minor improvements / changes that are not important for me to listen to.
the economist does a „world in brief” news summary daily, and having that for the papers that are relevant to me would be great!
Oh, that is nice idea! Do you think it would be more interesting for the community to reach out to scirate and integrate the podcasts there, or would it more interesting to try to scrape the scores from the scirate and integrate it to ekoAcademic?
The guy who runs scirate is a fellow quantum computing researcher (and all around friendly... fellow, lol). I can't speak for them, but I'm pretty sure they'd, at least, hear you out. The problem is more getting through the signal-to-noise of an academic's email:
Ah cool! Great to see accessibility stuff like this. Listening to papers makes it much easier for me to focus on the content.
I made my own little service that converts any webpage to hopefully the parsed content then uses Google TTS and then published it to a bucket and s3 feed and I listen to them on my phone before bed.
Nice idea - would love to have some kind of daily mix with all the papers from my field / some way to prioritise them automatically based on the most important ones I should have read
What do you think would be a good way to prioritise papers? It seems to be especially difficult when the papers are not yet rated by the users. We were thinking of some algorithm that would analyse the authors of the paper and their previous track record, but it feels somewhat unfair towards the new/young academics?
Super curious about your thoughts.
hmm that’s true - I think if you could get a measure of interest for the paper like views on arxiv or number of mentions online, that could be a good metric to use.
it’s also possible that the LLM will be able to determine well which results are important vs which are minor improvements / changes that are not important for me to listen to.
the economist does a „world in brief” news summary daily, and having that for the papers that are relevant to me would be great!
Integrate with scirate for that good good:
But seriously, I don't of another place that centers academics up-voting papers without... well... actually citing them.Oh, that is nice idea! Do you think it would be more interesting for the community to reach out to scirate and integrate the podcasts there, or would it more interesting to try to scrape the scores from the scirate and integrate it to ekoAcademic?
The guy who runs scirate is a fellow quantum computing researcher (and all around friendly... fellow, lol). I can't speak for them, but I'm pretty sure they'd, at least, hear you out. The problem is more getting through the signal-to-noise of an academic's email:
https://kunalmarwaha.com/about
Thank you for the contact. I will send him an email.
Do you have any thoughts on @joshny's comment? It is something we don't know exactly what would be the best strategy to deal with it.