AI Paper Atlas

Research map / Time series / Long-term forecasting

A Spiking Heterogeneous Harmonic Resonate-and-Fire State Space Model for Time Series

Kartikay Agrawal, Vaishnavi Nagabhushana, Abhijeet Vikram, Vedant Sharma, Ayon Borthakur

ICML 2026 · Time series › Long-term forecasting · approach: Spatiotemporal forecasting models

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
add heterogeneous learnable parameters to SH2RFSSM (ablation)SH2RFSSM · UEA six-dataset averageaccuracy (%): 61.7 -> 67.5Improved
make all parameters heterogeneous instead of a subset (ablation)SH2RFSSM · UEA six-dataset averageaccuracy (%): 67.5 -> 65.9Hurt
add learnable damping b (ablation)SH2RFSSM · UEA six-dataset averageaccuracy (%): 64.2 -> 63.5Hurt
use IM discretisation instead of explicit with heterogeneity in BHRF (ablation)BHRF · SHDSOPs: 4139.5 -> 2937.7Improved
use IM or IMEX discretisation instead of EX in HRF networks (ablation)BHRF · SHDaccuracy (%): 93.6±0.3 -> 93.5±0.7No clear effect
use IM discretisation instead of IMEX (ablation)SH2RFSSM · UEA six-dataset averageaccuracy (%): 65.3 -> 66.5Improved
use IMEX instead of IM discretisation (ablation)SH2RFSSM · PPG-DaLiAMSE x10^-2: 11.8 -> 8.5Improved
add learnable temporal-kernel spiking regressor with HRF layersSH2RFSSM · PPG-DaLiAMSE: Mamba 10.7 -> 8.5Improved
replace FFT/IFFT with HRF layerSpikF · ETTh1 efficiencylatency and energy: 7.77 ms -> 3.93 ms; 7.84 µJ -> 1.98 µJImproved
replace FFT/IFFT with HRF layerSpikF · ETTh1 and ETTm1MSE: 0.44 -> 0.443No clear effect
replace FFT/IFFT with HRF layerSpikF · ECLMSE: 0.183 -> 0.195Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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