Research map / Vision-language and multimodal / Cross-modal learning
Learning Signal-Agnostic Manifolds of Neural Fields
Yilun Du, Katherine M. Collins, Joshua B. Tenenbaum, Vincent Sitzmann
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add LLE loss to GEM (ablation) | GEM · Test-signal reconstruction across modalities | reconstruction performance | Improved |
| Add local isometry loss to GEM (ablation) | GEM · Test-signal reconstruction across modalities | reconstruction performance | Improved |
| Add reconstruction loss (ablation) | StyleGAN2 · CelebA-HQ test | MSE: 0.0044 -> 0.0041 | Improved |
| Add reconstruction loss (ablation) | StyleGAN2 · CelebA-HQ test | PSNR: 24.03 -> 24.29 | Improved |
| Add LLE loss after reconstruction loss (ablation) | StyleGAN2 + reconstruction loss · CelebA-HQ test | MSE: 0.0041 -> 0.0038 | Improved |
| Add LLE loss after reconstruction loss (ablation) | StyleGAN2 + reconstruction loss · CelebA-HQ test | PSNR: 24.29 -> 24.61 | Improved |
| Add local isometry loss (ablation) | StyleGAN2 with reconstruction and LLE losses · CelebA-HQ test | reconstruction performance | Hurt |
Closest papers by meaning
- The Sparse Manifold Transform (NeurIPS 2018 · similarity 0.86)
- ManifoldNet: A Deep Neural Network for Manifold-Valued Data With Applications (TPAMI 2020 · similarity 0.85)
- Neural Fields as Distributions: Signal Processing Beyond Euclidean Space (CVPR 2024 · similarity 0.84)
- Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves (NeurIPS 2026 · similarity 0.84)
- Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning (ICLR 2025 · similarity 0.83)
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations (NeurIPS 2025 · similarity 0.83)
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.
