
Sergey Shuvaev
@sergeyashuvaev
Postdoc at @penn | ex- @cshl, @mipt_eng | combining ML with neuroscience to build models of behavior
ID: 1327034283438067718
https://shuvaev.me/ 12-11-2020 23:43:31
103 Tweet
122 Takipçi
141 Takip Edilen



I really miss the times when ICML Conference rebuttals were limited to one page, and the reviewers' requests had to be scaled accordingly. The rebuttal period has started and many discussions are longer than papers🙃



Exciting week for the Alex Koulakov 's group! Two papers accepted on long-haul projects; three more conference papers accepted on recent work; final models submitted on an ML challenge! Congratulations to the team & collaborators; more updates coming shortly!


Paper Alert: A new theoretical framework for olfaction. Joint work with Hamza Giaffar, Sergey Shuvaev, and Alex Koulakov journals.plos.org/ploscompbiol/a…


Using LLMs to help with the writing is great, but you may want to edit their output - for its sanity. The number of the AISTATS Conference abstracts saying 'delve' - which I've automatically bid on as a strong negative - was sadly overwhelming.

Animals are born with innate abilities, such as spiders spinning webs. But where do these abilities come from? CSHL’s Tony Zador & Alexei Koulakov propose AI that could solve the mystery. cshl.edu/the-next-evolu…




How can we make progress in developing a general model of neural computation rather than a series of disjointed models tied to specific experimental circumstances, ask Eva Dyer and Blake Richards Blake Richards in the latest entry in our NeuroAI series. thetransmitter.org/neuroai/accept…

Happy to share that I've received AISTATS Conference Best Reviewer award! Excited to be helpful to the community

Dear NeurIPS Conference, would you please return search to bidding? Currently, I (we all - ?) get flooded with tons of poorly-matched papers from big umbrella areas of main expertise while better-matched niched papers can never be found, making all bids inevitably misplaced
