arXiv:2604.20917v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns. Existing benchmarks primarily focus on predicting program…
arXiv:2604.20920v1 Announce Type: new Abstract: Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include KV-cache selection or compression techniques. We instead provide an effective and end-to-end learnable bridge…
arXiv:2604.20915v1 Announce Type: new Abstract: Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history into states with…
arXiv:2604.20913v1 Announce Type: new Abstract: Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. Weight quantization to four bits or below reduces memory pressure, yet existing systems still dequantize weights…
arXiv:2604.20909v1 Announce Type: new Abstract: Downhole drilling telemetry presents a fundamental labeling asymmetry: surface sensor data are generated continuously at 1~Hz, while labeled downhole measurements are costly, intermittent, and scarce. Current machine learning approaches for downhole metric prediction universally adopt…
arXiv:2604.21698v1 Announce Type: cross Abstract: Persistent homology, a method from topological data analysis, extracts robust, multi-scale features from data. It produces stable representations of time series by applying varying thresholds to their values (a process known as a textit{filtration}). We…
arXiv:2604.20923v1 Announce Type: new Abstract: Grokking describes a delayed generalization phenomenon in which a neural network achieves perfect training accuracy long before validation accuracy improves, followed by an abrupt transition to strong generalization. Existing detection signals are indirect: weight norm…
arXiv:2604.21602v1 Announce Type: cross Abstract: Reservoir computing (RC) is an emerging recurrent neural network architecture that has attracted growing attention for its low training cost and modest hardware requirements. Memristor-based circuits are particularly promising for RC, as their intrinsic dynamics…
arXiv:2604.20943v1 Announce Type: new Abstract: We present SCM (Sleep-Consolidated Memory), a research preview of a memory architecture for large language models that draws on neuroscientific principles to address a fundamental limitation in current systems: the absence of persistent, structured, and…
arXiv:2604.21753v1 Announce Type: cross Abstract: Simulations of crystal growth are performed by using Convolutional Recurrent Neural Network surrogate models, trained on a dataset of time sequences computed by numerical integration of Allen-Cahn dynamics including faceting via kinetic anisotropy. Two network…
