arXiv preprints from January 1, 2026 through September 25, 2026 — 21:30:07 EST
The moka pot provides a familiar example of a thermally driven flow system in which heating, vapor pressure generation, and fluid extraction are strongly coupled. We present a minimal, dimensionless dynamical model describing the evolution of temperature, pressure, and extracted volume during moka pot brewing. The model consists of a...
Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional defense mechanisms remain ineffective as they overlook the unique reasoning dynamics of LRMs. In this work, we find...
Knowledge distillation has proven effective for model compression by transferring knowledge from a larger network called the teacher to a smaller network called the student. Current knowledge distillation in time series is predominantly based on logit and feature aligning techniques originally developed for computer vision tasks....
Reinforcement learning has become the primary paradigm for aligning large language models (LLMs) on complex reasoning tasks, with group relative policy optimization (GRPO) widely used in large-scale post-training. However, GRPO faces structural limitations in reasoning-heavy settings: sequence-level advantage normalization introduces...
Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and Transformer-based methods, have achieved strong performance on synthetic benchmarks. However, due to...
Uranus and Neptune are characterized by anomalously tilted and multi-dipole magnetic fields, which poses substantial challenges for elucidating the internal mechanisms generating magnetic fields. Recent investigations confirmed that superionic H2O is thermodynamically stable and constitutes the dominant H2O phase within their icy...
We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when learning multiple tasks sequentially. This method referred to as Group and Exclusive Sparsity based Continual Learning (GESCL) avoids...
Foundation models are powerful yet often opaque in their decision-making. A topic of continued interest in both neuroscience and artificial intelligence is whether some neurons behave like grandmother cells, i.e., neurons that are inherently interpretable because they exclusively respond to single concepts. In this work, we propose...
Long-range interactions and electric response are essential for accurate modeling of condensed-phase systems, but capturing them efficiently remains a challenge for atomistic machine learning. Traditionally, these two phenomena can be represented by static charges, that participate in Coulomb interactions between atoms, and dynamic...
Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality short clips but often fail to preserve entity identity and appearance when scenes change or when entities reappear after long temporal gaps. We present...
In this paper, we propose a high-efficiency deep joint source-channel coding (JSCC) method for video transmission based on conditional coding with asymmetric context. The conditional coding-based neural video compression requires to predict the encoding and decoding conditions from the same context which includes the same...
In this study, we introduce a quantum computing method that incorporates Ridglet transforms into quantum processing pipelines for financial time-series forecasting with Quantum Approximate Optimization Algorithm (QAOA)-based portfolio optimization. We propose a Quantum Ridgelet Neural Network (QRNN) model for forecasting time-series...
We establish a connection between Drinfeld modules and rank-metric codes, focusing on the case of semifield codes. Our method constructs rank-metric codes from linear subspaces of endomorphisms of a Drinfeld module acting on torsion submodules. We show that Sheekey's construction [She20] fits naturally into this framework, yielding a...
The rapid escalation of computing power driven by large-scale artificial intelligence is placing unprecedented demands on the bandwidth, latency, and energy efficiency of data-center interconnects (DCIs). Self-homodyne coherent (SHC) transmission is a promising architecture because it preserves the spectral efficiency of coherent...
We investigate mixed-state entanglement measures, namely reflected entropy, mutual information and logarithmic negativity, for two disjoint intervals in one-dimensional systems excited by a finite number of quasiparticles. While whole system is in a pure state, the two disjoint intervals are in a generically mixed state. To address...
Full-disk observations from missions such as the SDO and SOHO have enabled comprehensive studies of solar oscillations and dynamics. Interpreting helioseismic and photospheric data is complicated by systematic center-to-limb variations. To explore the physical origin of these variations, we perform local 3D radiative hydrodynamic...
Chain-of-Thought (CoT) prompting improves reasoning but often produces long and redundant traces that substantially increase inference cost. We present SyncThink, a training-free and plug-and-play decoding method that reduces CoT overhead without modifying model weights. We find that answer tokens attend weakly to early reasoning and...
We propose an efficient layer-specific optimization (ELO) method designed to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs). This approach addresses the common challenges of high computational cost and degradation of source language performance associated with traditional CP....
In extreme value analysis, tail behavior of a heavy-tailed data distribution is modeled by a Pareto-type distribution in which the so-called extreme value index (EVI) controls the tail behavior. For heavy-tailed data obtained from multiple population subgroups, or areas, this study efficiently predicts the EVIs of all areas using...
Job scheduling is widely used in real-world manufacturing systems to assign ordered job operations to machines under various constraints. Existing solutions remain limited by long running time or insufficient schedule quality, especially when problem scale increases. In this paper, we propose ReLA, a reinforcement-learning (RL)...
Emotional coordination is a core property of human interaction that shapes how relational meaning is constructed in real time. While text-based affect inference has become increasingly feasible, prior approaches often treat sentiment as a deterministic point estimate for individual speakers, failing to capture the inherent...
It is known that there exist theoretical limits on the mass of compact objects in general relativity. One is the Buchdahl limit for an object with an arbitrary equation-of-state that turns out to be the limit for an object with uniform density. Another one is the causal limit that is stronger than the Buchdahl limit and is related to...
A $k$-connectivity oracle for a graph $G=(V,E)$ is a data structure that given $s,t \in V$ determines whether there are at least $k+1$ internally disjoint $st$-paths in $G$. For undirected graphs, Pettie, Saranurak & Yin [STOC 2022, pp. 151-161] proved that any $k$-connectivity oracle requires $Ω(kn)$ bits of space. They asked whether...
Red supergiants (RSGs), representing a kind of massive young stellar population, have rarely been used to probe the structure of the Milky Way, mainly due to the long-standing scarcity of Galactic RSG samples. The Gaia BP/RP spectra (hereafter XP), which cover a broad wavelength range, provide a powerful tool for identifying RSGs. In...
Large Language Model (LLM)-based agents significantly extend the utility of LLMs by interacting with dynamic environments. However, enabling agents to continually learn new tasks without catastrophic forgetting remains a critical challenge, known as the stability-plasticity dilemma. In this work, we argue that this dilemma...