arXiv:2601.10863v1 Announce Type: new Abstract: Traditional time series forecasting methods optimize for accuracy alone. This objective neglects temporal consistency, in other words, how consistently a model predicts the same future event as the forecast origin changes. We introduce the forecast…
arXiv:2512.11145v2 Announce Type: replace Abstract: Analyzing and visualizing scientific ensemble datasets with high dimensionality and complexity poses significant challenges. Dimensionality reduction techniques and autoencoders are powerful tools for extracting features, but they often struggle with such high-dimensional data. This paper…
arXiv:2601.10823v1 Announce Type: new Abstract: Value level parallelism (VLP) has been proposed to improve the efficiency of large-batch, low-precision general matrix multiply (GEMM) between symmetric activations and weights. In transformer based large language models (LLMs), there exist more sophisticated operations…
arXiv:2601.10859v1 Announce Type: new Abstract: Inverse design tools such as Topology Optimization (TO) can achieve new levels of improvement for high-performance engineered structures. However, widespread use is hindered by high computational times and a black-box nature that inhibits user interaction.…
arXiv:2601.10820v1 Announce Type: new Abstract: Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets capturing the iterative and…
arXiv:2601.10810v1 Announce Type: new Abstract: Large language models (LLMs) currently suffer from parameter entanglement, where general reasoning capabilities (logic) and specific factual knowledge (facts) exist in a superposition state within shared weights. This coupling leads to the “memory wall,” where…
arXiv:2601.10801v1 Announce Type: new Abstract: We present a systematic study of Tensor Network (TN) models $unicode{x2013}$ Matrix Product States (MPS) and Tree Tensor Networks (TTN) $unicode{x2013}$ for real-time jet tagging in high-energy physics, with a focus on low-latency deployment on…
arXiv:2509.22023v2 Announce Type: replace Abstract: Despite their proficiency in various language tasks, Large Language Models (LLMs) struggle with combinatorial problems like Satisfiability, Traveling Salesman Problem, or even basic arithmetic. We address this gap through a novel trial & error approach…
arXiv:2601.10873v1 Announce Type: new Abstract: Deep neural networks constructed from linear maps and positively homogeneous nonlinearities (e.g., ReLU) possess a fundamental gauge symmetry: the network function is invariant to node-wise diagonal rescalings. However, standard gradient descent is not equivariant to…
arXiv:2511.09425v2 Announce Type: replace Abstract: Theoretically exploring the advantages of neural networks might be one of the most challenging problems in the AI era. An adaptive feature program has recently been proposed to analyze feature learning, the characteristic property of…
