Research map / Probabilistic and scientific modeling
Dynamical systems: research map
969 accepted papers on Dynamical systems in Probabilistic and scientific modeling, from ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), grouped into 3 clusters and 13 approaches. The busiest year so far is 2026.
Within Probabilistic and scientific modeling, its share grew from 11.1% in 2023–24 to 12.6% in 2025–26 (225 → 384 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Dynamical systems in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
Approaches and key papers
physical · physics · simulation · 427 papers
Approaches in this cluster:
- Physics-informed dynamics learning (127 papers)
Learns physical laws using Hamiltonian, Lagrangian and geometric neural dynamics models. - Latent dynamics models (111 papers)
Learns continuous-time or identifiable latent states from irregular or high-dimensional observations. - Latent-space control and planning (78 papers)
Plans and controls using learned latent dynamics, predictive coding and controlled SDEs. - Data assimilation from sparse observations (58 papers)
Reconstructs physical dynamics from sparse measurements using generative assimilation. - Stochastic population dynamics (53 papers)
Learns stochastic dynamics from samples with action matching and mean-field models.
Most cited and most cited since 2024:
- Interaction Networks for Learning about Objects, Relations and Physics (NeurIPS 2016 · 557 citations)
- Hamiltonian Neural Networks (NeurIPS 2019 · 447 citations)
- Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model (AAAI 2024 · 47 citations)
- Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators (NeurIPS 2024 · 23 citations)
brain · activity · neurons · 315 papers
Approaches in this cluster:
- Latent models of neural activity (70 papers)
Learns identifiable, behavior-aligned latent models of neural population activity. - Recurrent circuit models of inference (70 papers)
Explains Bayesian inference and learning with recurrent circuits and synaptic mechanisms. - Low-rank and diffusion neural dynamics (53 papers)
Extracts neural population dynamics using low-rank RNNs, latent diffusion and nonlinear embeddings. - Functional connectivity modeling (50 papers)
Infers interactions between brain regions with latent factor and multi-timescale models. - Synaptic plasticity learning rules (72 papers)
Explains learning via burst-dependent plasticity, interneurons, and feedback in recurrent neural circuits.
Most cited and most cited since 2024:
- Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition (CVPR 2016 · 267 citations)
- InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations (NeurIPS 2017 · 136 citations)
- BrainLM: A foundation model for brain activity recordings (ICLR 2024 · 45 citations)
- A Local-Ascending-Global Learning Strategy for Brain-Computer Interface (AAAI 2024 · 20 citations)
dynamical systems · nonlinear · linear dynamical · 227 papers
Approaches in this cluster:
- State-space inference for stochastic systems (104 papers)
Learns filters and amortized inference for nonlinear stochastic dynamical systems. - Switching and law-discovery dynamics (81 papers)
Models multiple dynamical regimes and discovers laws using recurrent switching or invariant models. - Stable contractive dynamics (42 papers)
Learns dynamics with stability guarantees through contraction analysis and control-oriented structure.
Most cited and most cited since 2024:
- Graph Networks as Learnable Physics Engines for Inference and Control (ICML 2018 · 271 citations)
- Neural Relational Inference for Interacting Systems (ICML 2018 · 267 citations)
- ODEFormer: Symbolic Regression of Dynamical Systems with Transformers (ICLR 2024 · 6 citations)
- Neural Continuous-Time Supermartingale Certificates (AAAI 2025 · 5 citations)
Related topics in Probabilistic and scientific modeling
- Uncertainty and Gaussian processes (1,162)
- Molecules and proteins (1,990)
- Variational and generative sampling (2,060)
- Treatment effects (421)
- Differential equations and PDEs (614)
- Causal discovery (830)
- Bayesian optimization (397)