AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov–Arnold Networks

Duc Hoang, Aarush Gupta, Philip Harris

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use KAN instead of parameter-matched MLP for drifting regression under fixed-pointonline learner on FPGA · Adaptive function approximation (<6,2>)cumulative regret: 97.6 -> 13.2Improved
use KAN instead of parameter-matched MLP for qubit readout under fixed-pointonline learner on FPGA · Single-shot qubit readout (<7,3>)accuracy (%): 50.4% -> 92.8%Improved
scale MLP up to MLP-L on qubit readout (ablation)MLP · Single-shot qubit readout (<7,3>)accuracy (%): 50.4% -> 49.0%No clear effect
scale MLP up to MLP-L on drifting regression (ablation)MLP · Adaptive function approximation (<6,2>)cumulative regret: 97.6 -> 48.3Improved
use KAN actor-critic instead of MLP actor-critic on non-stationary Acrobotonline actor-critic · Non-stationary Acrobot controlepisodic return: -500 -> -104Improved
use online DQN update with a large MLP instead of actor-critic (ablation)MLP on Acrobot · Non-stationary Acrobot controlepisodic return: -500 -> -298Improved
add fixed-point quantization at low bitwidth (ablation)MLP-L · Adaptive function approximation (2 integer bits)final cumulative regretHurt
add fixed-point quantization at low bitwidth (ablation)KAN · Adaptive function approximation (2 integer bits)final cumulative regretNo clear effect
increase KAN grid size G (ablation)KAN · Qubit readout (7-bit fixed-point)running accuracyImproved
increase MLP parameter count under fixed-point (ablation)MLP · Qubit readout (10-bit fixed-point)running accuracyNo clear effect
add LayerNorm or LSUV initialization to MLP (ablation)MLP · fixed-point online learningperformance gap to KANNo clear effect
keep updating online during angular drift instead of freezing the learner (ablation)KAN digit classifier · Digit classification with angular driftrunning accuracy: about 20% -> 80%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy