Tootfinder

Djokovic injured by falling bottle after easing past Moutet
A large metal bottle fell at speed on to Djokovic’s head.
The Serb fell to the ground, where he remained for around 40 seconds before he was guided away by security guards.
In video footage provided by tournament organisers, the bottle appeared to have fallen from the backpack of a fan as he reached down to high-five Djokovic.
The 36-year-old received stitches for a cut on his head and he did not speak with t…

Wie bij de NOS heeft er nu eigenlijk besloten dat er op de verkiezingsavond afgelopen donderdag van de #exitpoll alleen hele zetels getoond werden en geen percentages?
Stel dat ze gewoon een extra kolommetje erbij hadden gemaakt en de percentages hadden getoond, dan had niemand het 'nek-aan-nek' frame kunnen volhouden. Natuurlijk snap ik de '1 zetel foutmarge'. Als je net bove…

:kitten: Say hello to the new Kitten web site! 🎉
https://kitten.small-web.org
Like Kitten itself, it’s a baby but will be evolving quickly as they approach API version 1 together.
Enjoy!
💕
PS. Of course it’s written in Kitten itself. It doesn’t do anything fancy but here…

🪧 After backlash, ICSD board rejects school budget proposal, approves reduced version for public vote
https://ithacavoice.org/2024/04/after-backlash-icsd-board-rejects-school-budget-proposal-approve…

After backlash, ICSD board rejects school budget proposal, approves reduced version for public vote
ITHACA, N.Y. — Following pushback from taxpayers, the Ithaca City School District Board of Education rejected the district’s 2024-2025 school year budget proposal at its meeting late Tuesday night. Instead, […]

Today I am very confused about how the bird detector is failing to spot birds on the video stream but if I run it against the analysed frames (which are saved out in debug mode) using the same model, code, etc., it finds them.

"AI" isn't going to take over the world until it's reliable and going off my experiences with that, it's a long way off.

(and that's not even getting into the inability to use different models because REASONS)

This https://arxiv.org/abs/2405.18503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Sound content is an indispensable element for multimedia works such as video games, music, and films. Recent high-quality diffusion-based sound generation models can serve as valuable tools for the creators. However, despite producing high-quality sounds, these models often suffer from slow inference speeds. This drawback burdens creators, who typically refine their sounds through trial and error to align them with their artistic intentions. To address this issue, we introduce Sound Consistency…

Amazon has launched a new
“one-click to quit the union” tool,
and they’re relentlessly pushing it to every worker in their Coventry warehouse.
The QR code for the tool is displayed on each table in the canteen, in every meeting and training room, in every hallway, and every toilet, as well as shown every five minutes of the working day in screens at the centre of the warehouse.
If a worker scans the QR code and clicks the link, Amazon’s software automatically generates…

Legal challenge to Amazon UK's new "one-click to quit the union" tool - Foxglove
Following the news that Amazon warehouse workers in Coventry will soon get to vote on Trade Union recognition, Foxglove is supporting five workers at the Amazon UK Coventry warehouse to launch a legal challenge of Amazon’s latest union-busting tactic.

This https://arxiv.org/abs/2405.18503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Sound content is an indispensable element for multimedia works such as video games, music, and films. Recent high-quality diffusion-based sound generation models can serve as valuable tools for the creators. However, despite producing high-quality sounds, these models often suffer from slow inference speeds. This drawback burdens creators, who typically refine their sounds through trial and error to align them with their artistic intentions. To address this issue, we introduce Sound Consistency…

SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Koichi Saito, Dongjun Kim, Takashi Shibuya, Chieh-Hsin Lai, Zhi Zhong, Yuhta Takida, Yuki Mitsufuji
https://arxiv.org/abs/2405.18503

SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Sound content is an indispensable element for multimedia works such as video games, music, and films. Recent high-quality diffusion-based sound generation models can serve as valuable tools for the creators. However, despite producing high-quality sounds, these models often suffer from slow inference speeds. This drawback burdens creators, who typically refine their sounds through trial and error to align them with their artistic intentions. To address this issue, we introduce Sound Consistency…