Will Kolmogorov-Arnold Networks (KAN) be used/studied in at least five orals at NeurIPS 2027?
9
52
Ṁ193Ṁ100
2028
18%
chance
1D
1W
1M
ALL
Proxy for KANs "taking over" MLPs.
The question will resolve as N/A if NeurIPS 2027 does not take place.
To count, a paper needs to:
be an oral presentation;
use a neural network with a KAN architecture or close spiritual successor thereof, either as the main network or as a relevant baseline.
Announced papers not presented for one reason or another still count towards the yes resolution.
The closing date will be adjusted once the dates for NeurIPS 2027 are known.
Get Ṁ600 play money
Sort by:
Related questions
Will @firstuserhere coauthor a NeurIPS or ICML conference publication before end of 2024? (10,000 Mana subsidy)
28% chance
Will Manifold be cited in a paper from a top-tier AI lab or AI journal before 2025?
45% chance
Will we have an AI generated research paper accepted to > 1 top ML conference by 2026?
48% chance
Will any AI be able to explain formal language proofs to >=50% of IMO problems by the start of 2025?
63% chance
Will an AI co-author a mathematics research paper published in a reputable journal before the end of 2026?
59% chance
Will Anthropic and OpenAI collaborate substantially on a research paper before 2025?
51% chance
Will we have an AI generated research paper accepted to > 1 top ML conference by 2027?
62% chance
Will Neel Nanda's or Lee Sharkey's SERI MATS streams (Summer 2023) produce a NeurIPS or ICML conference publication?
31% chance
Will an AI be able to convert recent mathematical results into a fully formal proofs that can be verified by a mainstream proof assistant by 2025?
23% chance