The advance of medicine and technology has been a catalyst for the population’s longevity, reflected in the increase in elderly citizens. However, this increase also comes a burden on caregivers. To address this gap between need and accessibility, the motivation for this study arises, highlighting the challenges faced by an ageing population. This work presents […]
A Reference Architecture of Reinforcement Learning Frameworks
arXiv:2603.06413v1 Announce Type: cross Abstract: The surge in reinforcement learning (RL) applications gave rise to diverse supporting technology, such as RL frameworks. However, the architectural patterns of these frameworks are inconsistent across implementations and there exists no reference architecture (RA) to form a common basis of comparison, evaluation, and integration. To address this gap, we […]
RAC: Rectified Flow Auto Coder
arXiv:2603.05925v1 Announce Type: cross Abstract: In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by applying the decoder to flow timesteps. Its decoding path is straight and correctable, enabling step-by-step refinement. 2. The model inherently supports bidirectional inference, where […]
SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
arXiv:2602.11210v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage overhead, slow environment setup, and require container-management privileges. We propose SWE-MiniSandbox, a lightweight, container-free method that enables scalable […]
LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis
arXiv:2603.05904v1 Announce Type: cross Abstract: GPU design space exploration (DSE) for modern AI workloads, such as Large-Language Model (LLM) inference, is challenging because of GPUs’ vast, multi-modal design spaces, high simulation costs, and complex design optimization objectives (e.g. performance, power and area trade-offs). Existing automated DSE methods are often prohibitively expensive, either requiring an excessive […]
Kinetic-based regularization: Learning spatial derivatives and PDE applications
arXiv:2603.06380v1 Announce Type: cross Abstract: Accurate estimation of spatial derivatives from discrete and noisy data is central to scientific machine learning and numerical solutions of PDEs. We extend kinetic-based regularization (KBR), a localized multidimensional kernel regression method with a single trainable parameter, to learn spatial derivatives with provable second-order accuracy in 1D. Two derivative-learning schemes […]
RoboPocket: Improve Robot Policies Instantly with Your Phone
arXiv:2603.05504v2 Announce Type: replace-cross Abstract: Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy’s weaknesses, leading to inefficient coverage of critical state distributions. […]
Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
arXiv:2603.04413v2 Announce Type: replace-cross Abstract: Meaning in human language is relational, context dependent, and emergent, arising from dynamic systems of signs rather than fixed word-concept mappings. In computational settings, this semiotic and interpretive complexity complicates the generation and evaluation of meaning. This article proposes an interdisciplinary framework for studying meaning in large language model (LLM) […]
Performance Assessment Strategies for Language Model Applications in Healthcare
arXiv:2509.08087v2 Announce Type: replace-cross Abstract: Language models (LMs) represent an emerging paradigm within artificial intelligence, with applications throughout the medical enterprise. A comprehensive understanding of the clinical task and awareness of the variability in performance when implemented in actual clinical environments lays the foundation for the LM application assessment. Presently, a prevalent method for evaluating […]
Looking Through Glass Box
arXiv:2603.06272v1 Announce Type: cross Abstract: This essay is about a neural implementation of the fuzzy cognitive map, the FHM, and corresponding evaluations. Firstly, a neural net has been designed to behave the same way that an FCM does; as inputs it accepts many fuzzy cognitive maps and propagates them in order to learn causality patterns. […]
From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
arXiv:2603.06317v1 Announce Type: cross Abstract: Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally expensive or lack calibration. We propose a three-stage pipeline to post-train LLMs to efficiently infer calibrated uncertainty estimates for their […]
Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions
arXiv:2603.06330v1 Announce Type: cross Abstract: Behaviour Change Techniques (BCTs) are central to digital health interventions, yet selecting and delivering effective techniques remains challenging. Contextual bandits enable statistically grounded optimisation of BCT selection, while Large Language Models (LLMs) offer flexible, context-sensitive message generation. We conducted a 4-week study on physical activity motivation (N=54; 9 post-study interviews) […]