arXiv:2607. 27987v1 Announce Type: new Abstract: Tensor operations represent a cornerstone of modern scientific computing.
arXiv:2409. 17502v2 Announce Type: replace Abstract: Broadcast operations are widely used in scientific computing libraries, yet their mathematical formulation is often implicit and inconsistently represented in machine learning literature.
arXiv:2608. 17135v1 Announce Type: cross Abstract: Tensor networks are powerful formats for compressing large-scale data.
arXiv:2604. 09558v2 Announce Type: replace-cross Abstract: With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilation.
arXiv:2601. 16622v2 Announce Type: replace-cross Abstract: Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems.
arXiv:2606. 25975v1 Announce Type: new Abstract: Common first-order optimizers, such as Adam, implicitly treat each parameter block as an unstructured vector, which disregards the multilinear weight structure present in many modern machine learning models.
Common first-order optimizers, such as Adam, implicitly treat each parameter block as an unstructured vector, which disregards the multilinear weight structure present in many modern machine learning models. Recent work has shown that exploiting matrix structure can improve optimization dynamics.
arXiv:2505. 23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization with genuine reasoning.
arXiv:2604. 07242v3 Announce Type: replace Abstract: Despite deep learning models running well-defined mathematical functions, we lack a formal mathematical framework for describing model architectures.
arXiv:2606. 09707v1 Announce Type: new Abstract: As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increasingly challenging.
arXiv:2606. 07713v1 Announce Type: cross Abstract: The attention mechanism is the dominant computational bottleneck in modern transformer-based AI.
arXiv:2607. 25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models.
arXiv:2606. 08565v1 Announce Type: cross Abstract: Tensor networks provide efficient representations for compressing large neural networks.