Research map / Probabilistic and scientific modeling / Dynamical systems
Point process latent variable models of larval zebrafish behavior
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 |
|---|---|---|---|
| add continuous GP latent state x_n modulating transitions and intervals (ablation) | MRP+ · Zebrafish bouts held-out | test log likelihood (nats/bout): -23.12 -> -22.61 | Helped |
| add discrete latent bout-type state z_n (ablation) | GRP+ · Zebrafish bouts held-out | test log likelihood (nats/bout): -24.88 -> -23.12 | Helped |
| add latent mark embedding h_n (deep generative model of marks) (ablation) | MRP · Zebrafish bouts held-out | test log likelihood (nats/bout): -41.15 -> -23.12 | Helped |
| add discrete Markov states to gamma renewal process | GRP · Zebrafish bouts held-out | test log likelihood (nats/bout): -57.06 -> -41.15 | Helped |
| add autoregressive interval dependence (AR1/AR10) instead of independent gamma intervals | GRP · Zebrafish bouts held-out | test log likelihood (nats/bout): -57.06 -> -49.75 | Helped |
| increase AR order from 1 to 10 | AR · Zebrafish bouts held-out | test log likelihood (nats/bout): -50.01 -> -49.75 | Helped |
| add continuous GP latent state to MRP on synthetic data | MRP · Synthetic data | test marginal likelihood: -245.19 -> -226.50 | Helped |
| more training sequences (10 to 250) | GPM-MRP · Synthetic data | test marginal likelihood: -239.12 -> -226.50 | Helped |
| increase discrete states beyond B=8 and embedding dims beyond H=10 (ablation) | GPM-MRP · Zebrafish bouts held-out | held-out ELBO | No clear effect |
Closest papers by meaning
- Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish (NeurIPS 2026 · similarity 0.88)
- Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics (NeurIPS 2025 · similarity 0.87)
- Model Based Inference of Synaptic Plasticity Rules (NeurIPS 2024 · similarity 0.85)
- BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation (ICLR 2025 · similarity 0.84)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · similarity 0.84)
- ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafish (ICLR 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.