Research map / Architectures and efficiency / Attention and transformers
STNDT: Modeling Neural Population Activity with Spatiotemporal Transformers
Trung Le, Eli Shlizerman
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 spatial attention to model neuron covariation alongside temporal dynamics | NDT · MC_Maze | co-bps: 0.3676 -> 0.3862 | Improved |
| Add spatial attention to model neuron covariation alongside temporal dynamics | NDT · MC_RTT | co-bps: 0.2053 -> 0.2095 | Improved |
| Add spatial attention to model neuron covariation alongside temporal dynamics | NDT · Area2_Bump | co-bps: 0.2860 -> 0.2898 | Improved |
| Add spatial attention to model neuron covariation alongside temporal dynamics | NDT · DMFC_RSG | co-bps: 0.1886 -> 0.1940 | Improved |
| Add contrastive loss (ablation) | STNDT single · MC_Maze | co-bps: 0.3668 -> 0.3691 | Improved |
| Add contrastive loss (ablation) | STNDT ensemble · MC_Maze | co-bps: 0.3843 -> 0.3862 | Improved |
| Add contrastive loss (ablation) | STNDT single · MC_RTT | co-bps: 0.1865 -> 0.1865 | No clear effect |
| Add contrastive loss (ablation) | STNDT ensemble · MC_RTT | co-bps: 0.2065 -> 0.2095 | Improved |
| Add contrastive loss (ablation) | STNDT single · Area2_Bump | co-bps: 0.2765 -> 0.2818 | Improved |
| Add contrastive loss (ablation) | STNDT ensemble · Area2_Bump | co-bps: 0.2904 -> 0.2898 | Hurt |
| Add contrastive loss (ablation) | STNDT single · DMFC_RSG | co-bps: 0.1824 -> 0.1859 | Improved |
| Add contrastive loss (ablation) | STNDT ensemble · DMFC_RSG | co-bps: 0.1931 -> 0.1940 | Improved |
Closest papers by meaning
- Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution (NeurIPS 2024 · similarity 0.88)
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data (ICLR 2024 · similarity 0.87)
- BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation (ICLR 2025 · similarity 0.87)
- Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems (NeurIPS 2024 · similarity 0.87)
- Latent Diffusion for Neural Spiking Data (NeurIPS 2024 · similarity 0.87)
- Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder (NeurIPS 2025 · similarity 0.87)
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.
