Research map / Label-efficient and robust learning / Recognition and long-tail
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use a structured Koopman autoencoder with the spectral loss | Koopman autoencoder · Sprites | Acc: 99.99% -> 100% | Helped |
| Use a structured Koopman autoencoder with the spectral loss | Koopman autoencoder · Sprites | IS: 8.871 -> 8.999 | Helped |
| Use a structured Koopman autoencoder with the spectral loss | Koopman autoencoder · MUG | Acc: 81.16% -> 77.45% | Hurt |
| Use a structured Koopman autoencoder with the spectral loss | Koopman autoencoder · MUG | IS: 5.341 -> 5.569 | Helped |
| Use a structured Koopman autoencoder with the spectral loss | Koopman autoencoder · TIMIT | Static EER: 4.03% -> 4.46% | Hurt |
| Use a structured Koopman autoencoder with the spectral loss | Koopman autoencoder · TIMIT | Dynamic EER: 31.81% -> 26.78% | Hurt |
| Add the dynamic spectral penalty to the static spectral penalty (ablation) | KAE + L_stat · Static and dynamic swaps | Static-factor swap quality | Helped |
| Add the static spectral penalty to the dynamic spectral penalty (ablation) | KAE + L_dyn · Static and dynamic swaps | Static-factor swap quality | Helped |
| Add the full spectral loss instead of omitting it (ablation) | Vanilla KAE · Static and dynamic swaps | Static-factor swap quality | Helped |
Closest papers by meaning
- Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations (NeurIPS 2025 · similarity 0.91)
- Sequential Disentanglement by Extracting Static Information From A Single Sequence Element (ICML 2024 · similarity 0.89)
- Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models (NeurIPS 2024 · similarity 0.89)
- Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning (ICML 2024 · similarity 0.88)
- Disentangled Representation Learning via Flow Matching (NeurIPS 2026 · similarity 0.88)
- Factorized Diffusion Autoencoder for Unsupervised Disentangled Representation Learning (AAAI 2024 · similarity 0.88)
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.