arXiv:2603.23755v1 Announce Type: cross Abstract: Curriculum learning improves reinforcement learning (RL) efficiency by sequencing tasks from simple to complex. However, many self-paced curriculum methods rely on computationally expensive inner-loop optimizations, limiting their scalability in high-dimensional context spaces. In this paper, we propose Self-Paced Gaussian Curriculum Learning (SPGL), a novel approach that avoids costly numerical procedures […]
LLMORPH: Automated Metamorphic Testing of Large Language Models
arXiv:2603.23611v1 Announce Type: cross Abstract: Automated testing is essential for evaluating and improving the reliability of Large Language Models (LLMs), yet the lack of automated oracles for verifying output correctness remains a key challenge. We present LLMORPH, an automated testing tool specifically designed for LLMs performing NLP tasks, which leverages Metamorphic Testing (MT) to uncover […]
KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits
arXiv:2603.24101v1 Announce Type: cross Abstract: Digital circuits representation learning has made remarkable progress in the electronic design automation domain, effectively supporting critical tasks such as testability analysis and logic reasoning. However, representation learning for analog circuits remains challenging due to their continuous electrical characteristics compared to the discrete states of digital circuits. This paper presents […]
APreQEL: Adaptive Mixed Precision Quantization For Edge LLMs
arXiv:2603.23575v1 Announce Type: cross Abstract: Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and memory requirements, making it challenging to deploy these models on edge devices to ensure real-time responses and data privacy. Quantization […]
Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks
arXiv:2603.23646v1 Announce Type: cross Abstract: While recent work has benchmarked large language models on Swiss legal translation (Niklaus et al., 2025) and academic legal reasoning from university exams (Fan et al., 2025), no existing benchmark evaluates frontier model performance on applied Swiss regulatory compliance tasks. I introduce Swiss-Bench SBP-002, a trilingual benchmark of 395 expert-crafted […]
The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense
arXiv:2603.23791v1 Announce Type: cross Abstract: Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency and raise privacy concerns. We present the Cognitive Firewall, a three-stage split-compute architecture that distributes security checks […]
Deep Convolutional Neural Networks for predicting highest priority functional group in organic molecules
arXiv:2603.23862v1 Announce Type: cross Abstract: Our work addresses the problem of predicting the highest priority functional group present in an organic molecule. Functional Groups are groups of bound atoms that determine the physical and chemical properties of organic molecules. In the presence of multiple functional groups, the dominant functional group determines the compound’s properties. Fourier-transform […]
Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation
arXiv:2603.23903v1 Announce Type: cross Abstract: Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the diffusion inversion problem, which serves as a fundamental building block for bridging […]
Kirchhoff-Inspired Neural Networks for Evolving High-Order Perception
arXiv:2603.23977v1 Announce Type: cross Abstract: Deep learning architectures are fundamentally inspired by neuroscience, particularly the structure of the brain’s sensory pathways, and have achieved remarkable success in learning informative data representations. Although these architectures mimic the communication mechanisms of biological neurons, their strategies for information encoding and transmission are fundamentally distinct. Biological systems depend on […]
Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
arXiv:2603.24058v1 Announce Type: cross Abstract: Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis. Through systematic empirical investigation, we identify that the imbalanced attention allocation, both across modalities (i.e., vision and language) […]
Dual-Criterion Curriculum Learning: Application to Temporal Data
arXiv:2603.23573v1 Announce Type: cross Abstract: Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progression. Defining meaningful difficulty assessment measures is crucial and most usually the main bottleneck for effective learning, while also in many cases the employed […]
AI Generalisation Gap In Comorbid Sleep Disorder Staging
arXiv:2603.23582v1 Announce Type: cross Abstract: Accurate sleep staging is essential for diagnosing OSA and hypopnea in stroke patients. Although PSG is reliable, it is costly, labor-intensive, and manually scored. While deep learning enables automated EEG-based sleep staging in healthy subjects, our analysis shows poor generalization to clinical populations with disrupted sleep. Using Grad-CAM interpretations, we […]