Research map / Vision-language and multimodal / Cross-modal learning
OmniField: Conditioned Neural Fields for Robust Multimodal Spatiotemporal Learning
Kevin Valencia, Thilina Balasooriya, Xihaier Luo, Shinjae Yoo, David Keetae Park
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 Gaussian Fourier features (ablation) | OmniField · CIFAR-10 reconstruction | MSE: 0.0097 -> 0.0007 | Improved |
| add sinusoidal initialization of queries (ablation) | OmniField · CIFAR-10 reconstruction | MSE: 0.0011 -> 0.0007 | Improved |
| add ICMR instead of Mid-Fusion (ablation) | OmniField · CIFAR-10 reconstruction | MSE: 0.0053 -> 0.0007 | Improved |
| add Gaussian Fourier features (ablation) | OmniField · ClimSim-LHW Temperature | RMSE: 2.61 -> 1.07 | Improved |
| add sinusoidal initialization (ablation) | OmniField · ClimSim-LHW Temperature | RMSE: 1.08 -> 1.07 | No clear effect |
| add ICMR instead of Mid-Fusion (ablation) | OmniField · ClimSim-LHW Temperature | RMSE: 1.56 -> 1.07 | Improved |
| add Gaussian Fourier features (ablation) | OmniField · ClimSim-LHW Humidity | RMSE: 1.74 -> 0.66 | Improved |
| add sinusoidal initialization (ablation) | OmniField · ClimSim-LHW Humidity | RMSE: 0.71 -> 0.66 | Improved |
| add Gaussian Fourier features (ablation) | OmniField · ClimSim-LHW Wind | RMSE: 5.35 -> 4.86 | Improved |
| add ICMR instead of Mid-Fusion (ablation) | OmniField · ClimSim-LHW Humidity | RMSE: 0.82 -> 0.66 | Improved |
| use ICMR rather than Mid-Fusion for all-modality input | OmniField · ClimSim-THW Temperature | RMSE: 1.398 -> 1.073 | Improved |
| add humidity and wind inputs to temperature-only input (Mid-Fusion) | OmniField · ClimSim-THW Temperature | RMSE: 1.887 -> 1.398 | Improved |
Closest papers by meaning
- When to Align, When to Predict: A Phase Diagram for Multimodal Learning (NeurIPS 2026 · similarity 0.86)
- SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields (ICML 2025 · similarity 0.85)
- Balancing Multimodal Training Through Game-Theoretic Regularization (NeurIPS 2025 · similarity 0.84)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.84)
- Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness (NeurIPS 2026 · similarity 0.84)
- MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities (CVPR 2025 · similarity 0.84)
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.
