arXiv:2602.22220v2 Announce Type: replace-cross Abstract: Quotation recommendation aims to enrich writing by suggesting quotes that complement a given context, yet existing systems mostly optimize surface-level topical relevance and ignore the deeper semantic and aesthetic properties that make quotations memorable. We start from two empirical observations. First, a systematic user study shows that people consistently prefer […]
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
arXiv:2511.19365v2 Announce Type: replace-cross Abstract: Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer from slow training and inference, as they usually model both high-frequency signals and low-frequency semantics […]
WRAP++: Web discoveRy Amplified Pretraining
arXiv:2604.06829v2 Announce Type: cross Abstract: Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. However, existing approaches operate at the single-document level, rewriting individual web pages in isolation. This confines synthesized examples to intra-document knowledge, missing cross-document relationships and leaving facts with limited associative context. […]
Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
arXiv:2512.19253v4 Announce Type: replace-cross Abstract: We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantum-augmented architectures remains largely unexplored. First, we adapt a broad suite of unlearning methods to quantum settings, […]
The Detection-Extraction Gap: Models Know the Answer Before They Can Say It
arXiv:2604.06613v2 Announce Type: cross Abstract: Modern reasoning models continue generating long after the answer is already determined. Across five model configurations, two families, and three benchmarks, we find that 52–88% of chain-of-thought tokens are produced after the answer is recoverable from a partial prefix. This post-commitment generation reveals a structural phenomenon: the detection-extraction gap. Free […]
WRAP++: Web discoveRy Amplified Pretraining
arXiv:2604.06829v2 Announce Type: cross Abstract: Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. However, existing approaches operate at the single-document level, rewriting individual web pages in isolation. This confines synthesized examples to intra-document knowledge, missing cross-document relationships and leaving facts with limited associative context. […]
Pulmonary fibrosis biotech Avalyn Pharma files for IPO
A biotech developing inhaled formulations of approved pulmonary fibrosis pills wants to tap the public markets to fund its late-stage work. Avalyn Pharma submitted its pitch on Wednesday night for a …
Russia’s Forest Blizzard Nabs Rafts of Logins Via SOHO Routers
Heard of fileless malware? How about malwareless cyber espionage? Russia’s APT28 is spying on global organizations by modifying just one DNS setting in vulnerable routers.
An EEG-based digital biomarker for personalizing transcranial magnetic stimulation in major depressive disorder
npj Digital Medicine, Published online: 09 April 2026; doi:10.1038/s41746-026-02603-8 An EEG-based digital biomarker for personalizing transcranial magnetic stimulation in major depressive disorder
Multicenter validation and updating of the ELDER-ICU model for severity assessment in elderly critical illness
npj Digital Medicine, Published online: 09 April 2026; doi:10.1038/s41746-026-02472-1 Multicenter validation and updating of the ELDER-ICU model for severity assessment in elderly critical illness