Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@Techmeme@techhub.social
2025-06-09 17:55:55

Apple announces a new live translation feature across Messages, FaceTime, and Phone apps, but has not yet said how many languages will be supported (Rebecca Bellan/TechCrunch)
techcrunch.com/2025/06/09/appl

Apple introduces live translation across Messages, FaceTime, and Phone at WWDC 25 | TechCrunch
Apple is introducing Live Translation, powered by Apple Intelligence, for Messages, FaceTime and Phone calls. 

@arXiv_astrophSR_bot@mastoxiv.page
2025-06-03 07:39:30

Binarity at LOw Metallicity (BLOeM): Pipeline-Determined Physical Properties of OB Stars
J. M. Bestenlehner, Paul A. Crowther, V. A. Bronner, S. Simon-Diaz, D. J. Lennon, J. Bodensteiner, N. Langer, P. Marchant, H. Sana, F. R. N. Schneider, T. Shenar
arxiv.org/abs/2506.00117

Binarity at LOw Metallicity (BLOeM): Pipeline-Determined Physical Properties of OB Stars
We aim to determine the physical properties of OB stars from the multi-epoch VLT/FLAMES BLOeM spectroscopic survey of the Small Magellanic Cloud. We apply a pipeline designed to analyse large spectroscopic samples of OB stars to the co-added, initial 9 epochs of the BLOeM survey, utilising grids of synthetic model spectra computed with the stellar atmosphere code FASTWIND. 69 OB stars are excluded from the analysis owing to disk emission or significant contamination by secondaries in SB2 binari…

@arXiv_csSD_bot@mastoxiv.page
2025-06-04 07:46:28

TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models
Chetwin Low, Weimin Wang
arxiv.org/abs/2506.03099

TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models
In this paper, we present TalkingMachines -- an efficient framework that transforms pretrained video generation models into real-time, audio-driven character animators. TalkingMachines enables natural conversational experiences by integrating an audio large language model (LLM) with our video generation foundation model. Our primary contributions include: (1) We adapt a pretrained SOTA image-to-video DiT into an audio-driven avatar generation model of 18 billion parameters; (2) We enable infini…