Will a Kolmogorov-Arnold Network based model achieve SOTA on some significant machine learning tasks in 2024?
32
1kṀ2991resolved Mar 27
Resolved
NO1H
6H
1D
1W
1M
ALL
https://arxiv.org/abs/2404.19756
https://github.com/KindXiaoming/pykan?tab=readme-ov-file
https://news.ycombinator.com/item?id=40219205
This sounds big to me.
I'm not sure exactly how to set the criteria. Perhaps based on https://paperswithcode.com/sota?
Someone who knows more about ML benchmarks please chime in.
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Name | Total profit |
|---|---|---|
| 1 | Ṁ137 | |
| 2 | Ṁ88 | |
| 3 | Ṁ72 | |
| 4 | Ṁ28 | |
| 5 | Ṁ17 |
People are also trading
Related questions
Will a SOTA model be trained with Kolmogorov-Arnold Networks by 2029?
8% chance
Will a leading AI company productize Kolmogorov–Arnold Networks (KAN) by 2026?
13% chance
Will any model of the LMSYS chatbot arena top 30 at the end of 2025 use Kolmogorov-Arnold Networks (KAN)?
8% chance
Will Transformer based architectures still be SOTA for language modelling by 2026?
80% chance
Will Kolmogorov-Arnold Networks (KAN) be used/studied in at least five orals at NeurIPS 2027?
8% chance
Will humans create a SOTA AI model without Multi-Layer Perceptrons by 2029?
39% chance
Will a SOTA open-sourced LLM forecasting system make major use of quasilinguistic neural reps (QNRs) before 2027?
19% chance
Will an AI model achieve superhuman ELO on Codeforces by the 31 December 2025?
25% chance
Will a lab train a >=1e26 FLOP state space model before the end of 2025?
15% chance
Will an AI model outperform 95% of Manifold users on accuracy before 2026?
44% chance