EEGDM: EEG Representation Learning via Generative Diffusion Model arXiv:2508.14086v2 Announce Type: replace Abstract: While electroencephalogram (EEG) has been a crucial tool for monitoring the brain and diagnosing neurological disorders (e.g., epilepsy), learning meaningful representations from raw EEG signals remains challenging…
Towards Quantum Machine Learning for Malicious Code Analysis arXiv:2508.19381v1 Announce Type: new Abstract: Classical machine learning (CML) has been extensively studied for malware classification. With the emergence of quantum computing, quantum machine learning (QML) presents a paradigm-shifting opportunity to improve…
Which Spaces can be Embedded in $L_p$-type Reproducing Kernel Banach Space? A Characterization via Metric Entropy arXiv:2410.11116v3 Announce Type: replace-cross Abstract: In this paper, we establish a novel connection between the metric entropy growth and the embeddability of function spaces…
DETNO: A Diffusion-Enhanced Transformer Neural Operator for Long-Term Traffic Forecasting arXiv:2508.19389v1 Announce Type: new Abstract: Accurate long-term traffic forecasting remains a critical challenge in intelligent transportation systems, particularly when predicting high-frequency traffic phenomena such as shock waves and congestion boundaries…
General agents contain world models arXiv:2506.01622v3 Announce Type: replace-cross Abstract: Are world models a necessary ingredient for flexible, goal-directed behaviour, or is model-free learning sufficient? We provide a formal answer to this question, showing that any agent capable of generalizing…
Quantum-Classical Hybrid Molecular Autoencoder for Advancing Classical Decoding arXiv:2508.19394v1 Announce Type: new Abstract: Although recent advances in quantum machine learning (QML) offer significant potential for enhancing generative models, particularly in molecular design, a large array of classical approaches still face…
Vocoder-Projected Feature Discriminator arXiv:2508.17874v2 Announce Type: replace-cross Abstract: In text-to-speech (TTS) and voice conversion (VC), acoustic features, such as mel spectrograms, are typically used as synthesis or conversion targets owing to their compactness and ease of learning. However, because the…
Kolmogorov-Arnold Representation for Symplectic Learning: Advancing Hamiltonian Neural Networks arXiv:2508.19410v1 Announce Type: new Abstract: We propose a Kolmogorov-Arnold Representation-based Hamiltonian Neural Network (KAR-HNN) that replaces the Multilayer Perceptrons (MLPs) with univariate transformations. While Hamiltonian Neural Networks (HNNs) ensure energy conservation…
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies arXiv:2508.20072v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions to robot actions. However, prevailing VLA decoders either generate actions autoregressively…
Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention arXiv:2508.19414v1 Announce Type: new Abstract: We present a mechanistic case study of a format-dependent reasoning failure in Llama-3.1-8B-Instruct, where the model incorrectly judges “9.11” as larger than…
