AI Paper Atlas

Research map / Time series / Foundation models for time series

From Teacher Pathways to Invariant Manifolds: Consensus Subspace Distillation for TSFMs

Zexing Zhang, Tianyang Lei, Jichao Li, Yang Kewei

ICML 2026 · Time series › Foundation models for time series · approach: Time series foundation 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 uncertainty injection (K=4) (ablation)Consensus subspace distillation · Classification (Table 4)accuracy: 0.698 -> 0.704Improved
add uncertainty injection (K=8) (ablation)Consensus subspace distillation · Classification (Table 4)accuracy: 0.747 -> 0.752Improved
add uncertainty injection (K=12) (ablation)Consensus subspace distillation · Classification (Table 4)accuracy: 0.757 -> 0.761Improved
add uncertainty injection (K=4) (ablation)Consensus subspace distillation · Anomaly detection Adj. Best F1 (Table 4)Adj. Best F1: 0.645 -> 0.651Improved
add uncertainty injection (K=16) (ablation)Consensus subspace distillation · Anomaly detection Adj. Best F1 (Table 4)Adj. Best F1: 0.711 -> 0.716Improved
increase copied layers K from 4 to 8 (ablation)Consensus subspace distillation · Classification (Table 4)accuracy: 0.704 -> 0.752Improved
increase copied layers K from 8 to 12 (ablation)Consensus subspace distillation · Classification (Table 4)accuracy: 0.752 -> 0.761Improved
increase copied layers K from 12 to 16 (ablation)Consensus subspace distillation · Classification (Table 4)accuracy: 0.761 -> 0.758No clear effect
consensus subspace distillation instead of CRDStudent at 9.87% parameters · Forecasting horizon 96MAE: 0.344 -> 0.287Improved
consensus subspace distillation instead of CRDStudent at 9.87% parameters · Zero-shot classificationaccuracy: 0.610 -> 0.633Improved
consensus subspace distillation instead of SliceGPTMOMENT-Large compression · Long-horizon forecastingMAE: 0.528 -> 0.471Improved
consensus subspace distillation instead of SliceGPTMOMENT-Large compression · Zero-shot classification (Table 1)accuracy: 0.685 -> 0.633Hurt

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