arXiv preprints from January 1, 2026 through September 22, 2026 — 04:43:08 EST
On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation with privileged conditioning is limited by in-context learning capacity. We propose \textbf{RISE}...
Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-based screening. We evaluated whether $β$-variational autoencoder (VAE)-derived ECG representations can discriminate LGE+ from LGE- cardiomyopathic patients in a local cohort of 300...
Let $C$ be an $[n,k]_q$ maximum distance separable (MDS) code with $4\le k\le q-3$, and suppose that it has a $2$-transitive permutation automorphism group. In this paper we show that $n\le q+1$, so the MDS conjecture holds for this class of codes.
Automated reference-based evaluation methods play a critical role in assessing natural language generation systems. Existing meta-evaluation primarily measures agreement with human judgments or benchmark labels, providing limited insight into evaluator behavior under controlled conditions. We introduce behavioral correctness...
Data stores are widely used because they provide persistence, scalability, and fault tolerance with a simple interface. However, most data store applications configure the data store to use weak isolation to achieve scalable performance, resulting in sporadic unserializable executions that are incorrect or fail. Prior work uses...
Recent years have witnessed great advances in the reasoning ability of Large Language Models (LLMs). However, the reasoning processes of LLMs often exhibit uncertainty, where LLMs often produce a proliferation of divergent branches at each reasoning step even when fed the same prompting inputs, and certain branches exhibit evidently...
Reliable robot-to-human handover requires the robot to infer when the person is ready to receive the object, and release it safely, comfortably, and at the right time. This is challenging because visual observations alone may not disambiguate clear taking intent from accidental contact, weak grasping, wrong-direction forces, or...
Fully fine-tuning self-supervised learning (SSL) speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predominantly rely on MLP-based adapters whose fixed activation functions limit their representational expressiveness under tight parameter budgets. We propose...
Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that can do the job. We test that assumption. Eight teams per setting are formed independently from one base model on the same tasks, each agent keeping a private notebook across ten...
A software project is more than just code. Non-code artifacts often document the human processes and decisions behind source code. The rationale behind a library change, an architectural decision, a problem encountered by a user are all examples of information typically present in socio-technical artifacts (STAs), created and...
Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout - particularly layer dropout - has largely disappeared from large language models (LLMs)...
LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution and retry. We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent from its output tokens alone, with no access to logits,...
Emotion recognition using physiological signals plays a crucial role in well-being analysis, affective computing and human-computer interaction. This study investigates the performance of multiple machine learning models in classifying targets such as discrete emotions with varying granularity, valence and arousal using physiological...
We study latency-optimal file assignment in geo-distributed storage systems modeled as weighted graphs, where edge weights represent communication delays and each node stores one (possibly coded) file. Our goal is to minimize the average time required to retrieve an original file, taken uniformly over all nodes and files. We show that...
Full-field laser Doppler vibrometry (LDV) can reveal how bolt torque loss redistributes a frequency response function (FRF) over an entire structure rather than only at a few sensor positions. This work presents a screening procedure for a four-bolt aluminum plate using pointwise amplitude and phase exports of scanned H1 FRFs....
Robotic hands vary widely in anatomical fidelity and mechanical complexity, and these structural choices influence the coordination of joint motions and the difficulty of controlling the system. A unified framework is presented in which the kinematic and actuation stages are analysed separately and in composition, through the...
Multi-modal learning has demonstrated strong potential in medical applications by integrating heterogeneous data sources such as medical imaging, clinical records, and genomics to improve predictive performance and support clinical decision-making. However, advances in this area are often constrained by two key challenges: the limited...
We consider safety-critical control problems involving multiple requirements with different priorities and uncertainty in their evaluation. We represent these requirements using risk-aware rulebooks, where each requirement is assigned a risk measure and an acceptable threshold, and a priority relation is defined among the...
Flexible loads can enhance power system stability by providing reserves, but their limited energy capacity and uncertain availability distinguish them from conventional generators. To accommodate these characteristics, the Danish Transmission System Operator (TSO) recently introduced new reserve market rules that incorporate energy...
Performance Boosting (PB) is a control framework that, for a pre-stabilized system subject to $\mathcal L_p$ process disturbances, parametrizes the controllers that preserve closed-loop $\mathcal L_p$-stability through a causal $\mathcal L_p$-stable operator mapping reconstructed disturbances to corrective control actions. Although...
This paper develops a marginal pricing mechanism for adaptive robust look-ahead economic dispatch (LAED) under net-load uncertainty. In current market practice, deterministic multi-interval dispatch can misprice flexibility when forecast error is large. Fully adaptive robust (FAR) dispatch captures this uncertainty, but competing...
Background and Objective: External evaluation of medical-imaging AI is often collapsed into discrimination. We evaluated a computational protocol that separately tests discrimination, probability calibration, fixed operatingpoint transport, shortcut-associated signal, and limited-label recoverability for pediatric pneumonia...
The increasing penetration of renewable energy challenges frequency stability due to high variability and declining inertia. Traditional frequency security constrained dispatch methods fail to capture regional frequency heterogeneity and spatially correlated stochastic disturbances, resulting in inaccurate frequency security...
At low bitrates, neural speech codecs have limited capacity to encode all information needed for high-quality re construction, especially when relying solely on speech-derived representations. To address this limitation, this paper proposes a Semantic- and Visual-enhanced Speech Codec (SVSC), which in corporates semantic and visual...
Conformal counterfactual inference enables network operators to use logged telemetry to reliably answer 'what-if' questions about network operation. These answers typically take the form of prediction sets that contain, with a user-defined probability, the key performance indicators (KPIs) that would have been observed under...