It’s a difficult week at Thoughtworks. Some of my colleagues are now looking for new opportunities.

If you’ve worked with us before you know what we’re capable of.
And if you haven’t yet, well, my colleagues are the brightest, most talented people I've had the privilege to work with.

If you have open roles for developers, BAs, XDs, product people, or any shaped technologist especially in Brisbane, Sydney, Melbourne, or remote - please share them with me so I can pass them along to affected coworkers. #FediJobs #FediHire

It took 3 whole hours of wandering around the blazing hot saltpans just south of Bangkok, but I’ve finally clapped eyes on one of the most endangered shorebirds in the world: the SPOON-BILLED SANDPIPER!! 🥄🥄🥄

We are looking for 11 new PhD students in a wide range of fields! #signals #XAI #XR #bias #ML #SSL #NLP #FG #HCC Share with grads looking for a PhD: Join us in Denmark 👇 https://www.aicentre.dk/phd-openings

My friend and colleague Stefan Heinrich is hiring PhD students interested in language structure, and music and speech processing. If you want to do a PhD in a great environment in Copenhagen 🇩🇰 check out the vacancies http://stefanheinrich.net/jobs/ #PhdChat #ComputerScience #ComputationalLinguistics

After a conversation with somebody on here about Mastodon clients and filtering, I cleaned up my JavaScript Mastodon client code and put it up here:

https://github.com/FahimF/FediJS

It’s pure JavaScript — no libraries, no dependencies … except for FontAwesome and BootStrap. And my original aim was to keep the code simple and uncomplicated.

It doesn’t do much at the moment except to allow you to connect to a Fedi server and to fetch posts (and maybe favourites and bookmarks? I forget …)

I was fixing an issue in my variation of Tusker today (where going several levels deep into a conversation would cause a crash) and I realized just how far I’d have to go to get the JavaScript client to that level. It probably would be easier in some respects and having the code as JavaScript would mean that it would run on so many different platforms, but do I have the fortitude to work on yet another client?

I’m not sure … But I do feel the itch to actually finish the JS Client … I guess we’ll see …

In 1423, London mayor Dick Whittington established a 128-seater toilet that hung over the River Thames.

Japanese Landscape

2023-01-31 to 02-01 day 228/229 of doing art every day for a year (mostly – I took sick days off).

For more info, see the blog post at https://lmashton.com/japanese-landscape/

#ArtMatters #Procreate #DigitalArt #WomensArt
Digital artwork. In the foregro…

"Consistency Models. (arXiv:2303.01469v1 [cs.LG])" — A new family of generative models that achieve high sample quality without adversarial training that supports fast one-step generation by design.

Paper: http://arxiv.org/abs/2303.01469

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Samples generated by EDM (top),…

"3D generation on ImageNet. (arXiv:2303.01416v1 [cs.CV])" — A more detailed/accurate method to generate 3D images based on 2D input images.

Paper: http://arxiv.org/abs/2303.01416

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Selected samples from EG3D (Cha…

"Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation. (arXiv:2303.01311v1 [cs.CV])" — Generating random game characters simply based on text input instead of customizing a pre-created character's visual attributes.

Paper: http://arxiv.org/abs/2303.01311

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Game characters created by the …

"Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?. (arXiv:2303.01255v1 [cs.CV])" — Would the quality of generative AI tools be affected if the input images are generated by AI tools themselves? An initial (simulated) experiment to explore this question.

Paper: http://arxiv.org/abs/2303.01255

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Two sets of sample images — the…

"X&Fuse: Fusing Visual Information in Text-to-Image Generation. (arXiv:2303.01000v1 [cs.CV])" — Multiple ways to condition images prior to text-to-image generation to achieve better output results.

Paper: http://arxiv.org/abs/2303.01000

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
X&Fuse conditions the model on …

"Scalable Diffusion Models with Transformers. (arXiv:2212.09748v2 [cs.CV] UPDATED)" — Creating diffusion models that use transformers instead UNets.

Paper: http://arxiv.org/abs/2212.09748
Code: https://github.com/facebookresearch/DiT

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Diffusion models with transform…

A few photos from autumn. Thanks for all the kind comments about the winter photos. 😌

Hi everyone, I'm a totally blind electronic musician. Looking for a audio, developer fluent in C++ d to help me with a very special open source project to assist blind people with electronic music production. If you can help me, or know anyone in your network who can please reach out and get at me. Thanks very much everyone :-) #electronic music :-)

"Collage Diffusion. (arXiv:2303.00262v1 [cs.CV])" — Creating harmonious and cohesive output images based on a text prompt and a collection of images as input.

Paper: http://arxiv.org/abs/2303.00262

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Collage Diffusion creates globa…

"PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing. (arXiv:2303.00137v1 [cs.CV])" — Generating realistic shadows and reflections using 2D images and deep learning techniques.

Paper: http://arxiv.org/abs/2303.00137

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
PixHt-Lab renders realistic ref…

"Magic: Multi Art Genre Intelligent Choreography Dataset and Network for 3D Dance Generation. (arXiv:2212.03741v3 [cs.CV] UPDATED)" — A choreography dataset and a network for generating 3D dance segments based on a music clip as input.

Paper: http://arxiv.org/abs/2212.03741

Note: v3 of the paper is currently not available in PDF form on arXiv.

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A conceptual overview of Magic.…

A total of 116 papers in the cs.CV category on arXiv.org today — 82 new, 34 updated.

Away we go to read some more!

#AI #CV #NewPapers #DeepLearning #MachineLearning

Variation on the Lotus theme.

Little lilypads from a walk along the river.

#photography
#RuralSouth
#watercolors