arXiv preprints from January 1, 2026 through September 14, 2026 — 12:13:00 EST
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...
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...
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 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...
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....
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...
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...
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...
Text-to-Image In-Context Learning (T2I-ICL) enables customized image synthesis via interleaved text-image examples but faces two mutually reinforcing bottlenecks, compliance failure and prior-dominated hallucination, that form a vicious cycle degrading generation quality. Existing methods rely on tailored training, which limits...
Many real-world software tasks require exact transcription of provided data into code, such as cryptographic constants, protocol test vectors, allowlists, and calibration tables. These tasks are operationally sensitive because small omissions or alterations can remain silent while producing syntactically valid programs. This paper...
Topic modeling is a crucial technique for extracting latent themes from unstructured text data, particularly valuable in analyzing survey responses. However, traditional methods often only consider free-text responses and do not natively incorporate structured or categorical survey responses for topic modeling. And they produce...
Defect segmentation is central to computer vision based inspection of infrastructure assets during both construction and operation. However, deployment remains limited due to scarce pixel-level labels and domain shift across environments. We introduce CrackSegFlow, a controllable Flow Matching synthesis method that renders synthetic...
Artificial neural network operators (ANNOs) have been widely used for approximating deterministic input-output functions; however, their extension to random dynamics remains comparatively unexplored. In this paper, we construct a new class of \textbf{Kantorovich-type Stochastic Neural Network Operators (K-SNNOs)} in which randomness...
Accurate and high-resolution precipitation nowcasting from radar echo sequences is crucial for disaster mitigation and economic planning, yet it remains a significant challenge. Key difficulties include modeling complex multi-scale evolution, correcting inter-frame feature misalignment caused by displacement, and efficiently capturing...
In evolutionary robotics, robot morphologies are designed automatically using evolutionary algorithms. This creates a body-brain optimization problem, where both morphology and control must be optimized together. A common approach is to include controller optimization for each morphology, but starting from scratch for every new body...
The rapid development of large language models has led to an increase in AI-generated text, with students increasingly using LLM-generated content as their own work, which violates academic integrity. This paper presents an evaluation of AI text detection methods, including both traditional machine learning models and...
Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular,...
Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches. We introduce a performance-aware, closed-loop solution in the NNGPT ecosystem of projects that enables LLMs to autonomously engineer...
Evolutionary Robotics offers the possibility to design robots to solve a specific task automatically by optimizing their morphology and control together. However, this co-optimization of body and control is challenging, because controllers need some time to adapt to the evolving morphology - which may make it difficult for new and...