arXiv:2601.18069v1 Announce Type: cross Abstract: Ensuring timely and semantically accurate information delivery is critical in real-time wireless systems. While Age of Information (AoI) quantifies temporal freshness, Version Age of Information (VAoI) captures semantic staleness by accounting for version evolution between transmitters and receivers. Existing VAoI scheduling approaches primarily focus on minimizing average VAoI, overlooking rare […]
CUROCKET: Optimizing ROCKET for GPU
arXiv:2601.17091v1 Announce Type: cross Abstract: ROCKET (RandOm Convolutional KErnel Transform) is a feature extraction algorithm created for Time Series Classification (TSC), published in 2019. It applies convolution with randomly generated kernels on a time series, producing features that can be used to train a linear classifier or regressor like Ridge. At the time of publication, […]
Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
arXiv:2601.17111v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe that even well-trained MoE models exhibit significantly imbalanced routing. This behavior is arguably natural-and even desirable – as imbalanced routing allows models to concentrate domain-specific knowledge within a subset of […]
TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion
arXiv:2601.17178v1 Announce Type: cross Abstract: Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks. We introduce TrojanGYM, an agentic, LLM-driven framework that automatically curates HT insertions to expose detector blind spots while preserving design correctness. Given high-level HT specifications, a suite of cooperating LLM […]
The Viscosity of Logic: Phase Transitions and Hysteresis in DPO Alignment
arXiv:2601.17260v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) is often tuned as if increasing alignment pressure (controlled by $beta$) yields progressively “better” behavior. We instead treat $beta$ as a control parameter and densely sweep it for three 7B open-weight families under a fixed DPO recipe. In Mistral, capability is sharply non-monotonic: aggregated logic-probe margins […]
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment
arXiv:2601.17329v1 Announce Type: cross Abstract: Preference-based alignment like Reinforcement Learning from Human Feedback (RLHF) learns from pairwise preferences, yet the labels are often noisy and inconsistent. Existing uncertainty-aware approaches weight preferences, but ignore a more fundamental factor: the reliability of the emphanswers being compared. To address the problem, we propose Conformal Feedback Alignment (CFA), a […]
Diversified Scaling Inference in Time Series Foundation Models
arXiv:2601.17376v1 Announce Type: cross Abstract: The advancement of Time Series Foundation Models (TSFMs) has been driven primarily by large-scale pre-training, but inference-time compute potential remains largely untapped. This work systematically investigates two questions: how do TSFMs behave under standard sampling-based inference scaling, and can controlled sampling diversity enhance performance? We first examine the properties of […]
The 17% Gap: Quantifying Epistemic Decay in AI-Assisted Survey Papers
arXiv:2601.17431v1 Announce Type: cross Abstract: The adoption of Large Language Models (LLMs) in scientific writing promises efficiency but risks introducing informational entropy. While “hallucinated papers” are a known artifact, the systematic degradation of valid citation chains remains unquantified. We conducted a forensic audit of 50 recent survey papers in Artificial Intelligence (N=5,514 citations) published between […]
BMDS-Net: A Bayesian Multi-Modal Deep Supervision Network for Robust Brain Tumor Segmentation
arXiv:2601.17504v1 Announce Type: cross Abstract: Accurate brain tumor segmentation from multi-modal magnetic resonance imaging (MRI) is a prerequisite for precise radiotherapy planning and surgical navigation. While recent Transformer-based models such as Swin UNETR have achieved impressive benchmark performance, their clinical utility is often compromised by two critical issues: sensitivity to missing modalities (common in clinical […]
Real-Time Trend Prediction via Continually-Aligned LLM Query Generation
arXiv:2601.17567v1 Announce Type: cross Abstract: Trending news detection in low-traffic search environments faces a fundamental cold-start problem, where a lack of query volume prevents systems from identifying emerging or long-tail trends. Existing methods relying on keyword frequency or query spikes are inherently slow and ineffective in these sparse settings, lagging behind real-world shifts in attention. […]
Time-Varying Causal Treatment for Quantifying the Causal Effect of Short-Term Variations on Arctic Sea Ice Dynamics
arXiv:2601.17647v1 Announce Type: cross Abstract: Quantifying the causal relationship between ice melt and freshwater distribution is critical, as these complex interactions manifest as regional fluctuations in sea surface height (SSH). Leveraging SSH as a proxy for sea ice dynamics enables improved understanding of the feedback mechanisms driving polar climate change and global sea-level rise. However, […]
FedCCA: Client-Centric Adaptation against Data Heterogeneity in Federated Learning on IoT Devices
arXiv:2601.17713v1 Announce Type: cross Abstract: With the rapid development of the Internet of Things (IoT), AI model training on private data such as human sensing data is highly desired. Federated learning (FL) has emerged as a privacy-preserving distributed training framework for this purpuse. However, the data heterogeneity issue among IoT devices can significantly degrade the […]