scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python

The introduction of Low-Rank GEMM presents a significant advancement in matrix multiplication efficiency, utilizing low-rank approximations to reduce computational complexity from cubic to sub-quadratic levels while leveraging FP8 precision on NVIDIA RTX 4090 hardware. This method achieves remarkable performance metrics, including up to 378 TFLOPS and 75% memory savings compared to traditional approaches.

PrismSSL is a newly released Python library that consolidates various self-supervised learning methods across multiple modalities, including audio, vision, and graphs, into a single modular codebase. It allows users to easily install, configure, and run pretext training with minimal code, while also enabling the reproduction of benchmarks and extension of the framework with new methods.

TorchQuantumDistributed (tqd) has been introduced as a PyTorch-based library designed for accelerator-agnostic differentiable quantum state vector simulation at scale, facilitating the study of learnable parameterized quantum circuits with high qubit counts.

A new differentiable extension of the VEROS ocean model has been introduced, allowing for automatic differentiation through its dynamical core. This development enhances the model's compatibility with the JAX autodifferentiation framework and includes key modifications to ensure numerical consistency. Two applications demonstrate its utility: optimizing initial ocean states and calibrating physical parameters from model observations.

Recent advancements in seismic wave propagation simulations have highlighted the use of neural operators, which significantly accelerate the process of full waveform inversion. This method, leveraging machine learning, offers a faster alternative to traditional computational techniques like finite difference or finite element methods.