This paper proposes a preconditioning layer for stable weight conditioning in LLM training.

This paper derives a method to predict and mitigate intruder dimensions caused by LoRA fine-tuning in deep learning models, improving performance and reducing forgetting.

The paper aims to determine the weight spectrum of Reed-Muller codes $RM(m-7,m)$, focusing on $RM(7,14)$. Although they found most weights, eight remain unidentified, which is essential for answering…

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

The paper proposes Fuzzy-Function Programming and introduces Program-as-Weights (PAW), a compact, locally-executable neural artifact for everyday programming tasks.

The paper introduces and analyzes several novel data appraisal metrics, including the Vendi Score and matrix spectral functions, demonstrating that efficient optimization techniques make these metrics…

This paper introduces the Distributed Truncated Spectral Transform (DTST) for Fourier Neural Operators (FNOs), achieving significant speedups in distributed computing.

This paper explains the concept of 'weight-norm criticality' in deep neural network training, which is a stability issue induced by the interaction between normalization and weight decay.

This paper proves an inverse-polynomial spectral-gap bound for the lazy swap chain on binary matrices with prescribed row and column sums, which is a standard sampler for fixed-margin null models.

This paper presents a method for identifying probabilistic structures from empirical probability tensors using algebraic statistics and Kronecker-stack class of configuration matrices.

The scaling exponent in neural scaling laws is not fixed but systematically depends on the optimizer used, with preconditioned optimizers generally yielding steeper scaling.

The paper introduces SPECTRA, a scalable framework for generating large, synthetic, and controllable information retrieval test collections, demonstrating its ability to expose system scaling and fail…

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

The paper proposes the Morlet Spectral Transformer (MST), a novel architecture that effectively decodes cross-subject emotion from EEG by designing specialized spectral and spatial representations, ou…

The paper proposes PagedWeight, a method for managing Mixture-of-Experts (MoE) language model serving in KV-cache-intensive scenarios, achieving FP16-equivalent accuracy with up to 72.0% GPU memory sa…