the General Physics Transformer
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Towards a Physics Foundation Model
arXiv:2509.13805v4 Announce Type: replace Abstract: Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be transformative - democratizing access to high-fidelity simulations, accelerating scientific discovery, and eliminating the need for specialized solver development. Yet current...
EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs
Announce Type: new Abstract: Deep learning surrogates for 3D Partial Differential Equations (PDEs) often fail to generalize across geometric transformations because they depend heavily on specific coordinate systems. While equivariant networks offer a solution, they typically rely on local operations in the spatial domain, making the global receptive field, which is essential for PDE dynamics, computationally expensive. Conversely, Fourier Neural Operators (FNOs) efficiently capture global...
Free energy Estimation on Any State Space
arXiv:2605.31063v1 Announce Type: cross Abstract: Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimation, quasistatic integration, to finite-time averaging. [He and Du et al., 2025] learns neural transports to significantly accelerate the efficiency in the finite-time regime.
Free energy Estimation on Any State Space
arXiv:2605.31063v1 Announce Type: cross Abstract: Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimation, quasistatic integration, to finite-time averaging. [He and Du et al., 2025] learns neural transports to significantly accelerate the efficiency in the finite-time regime.
On the training of physics-informed neural operators for solving parametric partial differential equations
Announce Type: new Abstract: Physics-informed neural operators (PINOs) aim to learn solution operators for partial differential equations by using the governing physics as supervision, rather than relying solely on paired input-output simulation data. By incorporating physical constraints into the training objective, PINOs combine the cross-instance generalization of neural operators with the data efficiency of physics-informed learning. Despite this promise, how to train PINOs efficiently...
On the training of physics-informed neural operators for solving parametric partial differential equations
Announce Type: cross Abstract: Physics-informed neural operators (PINOs) aim to learn solution operators for partial differential equations by using the governing physics as supervision, rather than relying solely on paired input-output simulation data. By incorporating physical constraints into the training objective, PINOs combine the cross-instance generalization of neural operators with the data efficiency of physics-informed learning. Despite this promise, how to train PINOs efficiently...
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
arXiv:2606.08952v1 Announce Type: new Abstract: Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models.
Building The Ph(ysical)AI Layer Of Machine Intelligence
arXiv:2606.04106v1 Announce Type: new Abstract: Foundation models achieve generalization through massive-scale training on diverse data, but have limitations with transfer to truly unseen domains without paired training data. We propose principle-driven foundation models that encode signal-theoretic principles (Fourier decomposition, energy conservation, symmetry) rather than learn untethered statistical correlations. We hypothesize that domains differ not in fundamental physics, but in...
Human-Like Neural Nets by Catapulting
Human-like Neural Nets by Catapulting Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparameterized NNs to trigger catapulting/grokking. Over-parameterization as a route to true generalization would resolve many outstanding mysteries of artificial versus natural intelligence. There are many mysteries about deep learning and human intelligence, but we could describe the biggest anomaly this way: why are...
Spatial Deformation Mechnisim of Meta-Atom Coupling and Scaling
arXiv:2606.04796v1 Announce Type: new Abstract: Metasurfaces enable precise manipulation of light-matter interactions, and meta-atom coupling and scaling dominates their resonant properties and functional responses. Conventionally, coupled-mode theory (CMT), coupled dipole theory (CDT) and full-wave simulation are widely adopted to analyze such coupling effects.