"DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer. (arXiv:2303.03755v1 [cs.CV])" — Using diffusion models to create visual layouts as part of graphics design.

Paper: http://arxiv.org/abs/2303.03755

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of our Joint Discrete-…

I had a peaceful trip and was able to spend a good amount of time with some of the birds. Here’s the Santa Cruz Island superstar: the Island scrub-jay. Also three separate people recognized me from my Twitter photo account!

I got laid off yesterday. We'll be ok, but it still sucks. Tough time to be on the market.

I'm giving myself space this week, but applied to a role yesterday 🤞🏻

Looking for roles in open source as a senior IC, management in a larger org, or nonprofit leadership. I'm most known for partnerships, community building, nonprofit operations, and program management, and I hold my own in compliance and media relations.

Resume etc: https://joshsimmons.com

#OpenSource #GetFediHired

Hello! I have just discovered the delightful #MarshMadness hashtag. Here's a #beaver #pond and #marsh at Barnes Camp on the road up to Smugglers Notch, #Vermont. Mt. Mansfield, the state's highest peak is to the left. August 2022. #GreenMtns #MountainMonday

@agneev The version I’m using is the App Store version — so no joy there, I’m afraid 🙂

@davemark

@davemark Just switched to it today after the announcement 🙂 I’ve been using Spark but Spark’s been getting slower and slower as time went on and it was becoming annoying. So switched over to Outlook today.

It’s much faster, but there does seem to be a delay (a good 1 - 2 minutes) in receiving Gmail e-mails when compared to Spark which I’m still running on iOS. Other than that, it seems to be solid and works well 🙂

"Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis. (arXiv:2303.02460v1 [cs.CV])" — What it says in the title, an improved dataset for agricultural pattern analysis.

Paper: http://arxiv.org/abs/2303.02460

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Left: Full-field imagery (RGB-o…

"Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later. (arXiv:2303.02490v1 [cs.CV])" — An exploration of the the theory that diffusion models generate images like painters creating a painting: that it involves first committing to an outline, and then adding in finer details.

Paper: http://arxiv.org/abs/2303.02490

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Characteristics of image genera…

"All are Worth Words: A ViT Backbone for Diffusion Models. (arXiv:2209.12152v3 [cs.CV] UPDATED)" — A simple and general ViT-based architecture for image generation with diffusion models which is capable of unconditional and class-conditional image generation, as well as text-to-image generation tasks.

Paper: http://arxiv.org/abs/2209.12152

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Text-to-image generation on MS-…

Imposter Syndrome is very real. I don't know about you guys, but I basically spend a large portion of my time thinking about it.

I think we as a society spend too much time considering and focusing on our transactions. "Am I enough?" "Do I deserve this nice thing?" "Someone liked my toot - will they figure out I don't have everything together?"

It's interesting when you think about it because if I were to ask you if you have those thoughts - most people would agree. "Sure, that happens sometimes" or "Of course, everyone feels like that sometimes..." right?

If we can agree that everyone feels like that, can we then begin to challenge if people have TIME to be that concerned about you? They are busy worried about their own problem and figuring out if you think THEY are enough.

You are enough. You might stumble, you might need to learn more. But that's okay. That's life. We're all out here doing our best. Some of us seem to be doing better or worse than you - but trust me, that is just the public facade.

Be kinder to yourself. You deserve it.

#Breathe

#Flowers #FlowerPhotography #Nature #NaturePhotography #Photography #Fotografia #MastoArt #AYearForArt #ArtMatters #1000Breaths

Expand to see the full vertical image.

I miss my nurse & science bird app communities. Still looking for me people on here

Help me find/follow you #nurse #science #academia

I was in search of some colour today, Glastonbury Abbey this morning.
#glastonbury #somerset #glastonburyabbey #abbey #daffodils

Spring
By Olha Darchuk

#nature #landscape #trees #painting #mastoart #mountains

@EPluribusPlus My question to you would be, why are we bringing in animals into the discussion? 🙂

The original question was whether what people call AI is actually intelligent. You seemed to think so. I don’t think so and mentioned that AI will just conjure information wholesale for you.

You countered with humans hallucinate too. (Though to be honest, these ML systems are not hallucinating — that’s just what some people have decided to call it — they are just generating information).

You also mentioned animals at this point. Now you mention “if we consider all animals to be intelligent that lowers the bar”. But my question is why do we need to bring animals into this at all?

Are current ML systems capable of reasoning? That probably would be what would qualify them to be called “intelligent” would be my guess. As far as I can tell, they are not capable of reasoning at this point. All they are capable of is looking at patterns and making decisions based on statistics.

This would probably be the same difference as a human who has learnt things by rote and is able to parrot back that information but cannot tell you the implications of that information beyond what they memorised. If they can’t draw inferences between two pieces of the information they’ve acquired and can only parrot it back at you, or worse, will invent stuff because they don’t know something, then that’s not intelligence 🙂

@EPluribusPlus And why would we want animals to be just like us? Also, do we know for a fact that they lack language, capacity to plan etc.? There are various counter-examples I can provide for each of those 🙂

Why does another species have to do things exactly the way we do or in a way we understand? Why are we so human-centric? 😛

A little bit more on the Edge browser and all the interesting activities it has built-in …

It has this little page of activities that you can try. One of them was to solve a tile puzzle — an image split into tiles and mixed up that you have to arrange corectly.

Once you complete the image, you get more information about the image and hotspots on the image you can click to get more information. If you click on a hotspot, you are taken to a Bing page with photos, relevant links, and a sidebar with additional links that you can explore.

As somebody who loves learning esoteric things, this just feels like the first time I discovered an encyclopaedia, but a lot more fun 🙂

#Edge #Browser #Gamification #Bing
An image of a tile/card which s…
A beautiful image of a bay with…
A Bing page with information ab…

@EPluribusPlus And that’s another thing I hate about how people approach machine learning systems — saying that they hallucinate. They do not hallucinate. They just give you fake information because they are just generators which put text together and are unable to distinguish between what is real and what is fake since they have no intelligence.

We really need to stop anthropomorphizing these systems 🙂 They are not people. Just systems which have been taught to recognise patterns but do not have the capability to reason about these patterns.

As for the animal kingdom, would you care to give some examples? I can’t comment on your point without knowing what you consider to be systemic failure in logic …

@EPluribusPlus Just getting the answers right doesn’t make something intelligent — you have to be able to critically evaluate facts and to be able to distinguish between things. These systems are not capable of that. Try coding with the help of a large language model for long enough and you’ll find that it gives you inventented answers.

If the system were truly ingelligent, it would know the difference between fact and fiction. So, while I respect your right to have your own opinion, I don’t believe it’s correct to say something is intelligent just because it can regurgitate facts, especially when it invents “facts” if it doesn’t have them.

I’ve been peripherally aware of the existence of the Edge browser, but I’ve not really used it till now. (Or, if I tried it originally, I just used it once and then uninstalled — that’s always possible since I try out a lot of stuff …)

I just installed the Edge browser (yes, it’s available on macOS) and was rather pleasantly surprised. It integrates a lot of tools I use all the time, has a better search interface, and has a bunch of game/activities which gives you that little endorphin rush while also helping you learn a lot more …

Showed it to my wife today and she seems to be really taken with it too. I think we’ll be playing around with this for a few more days at least!

And this kind of brings me to what I originally wanted to say. It’s rather interesting that Microsoft these days is going the “embrace all” route. Their stuff is not available just on Windows but is available on macOS too, while Apple generally sticks to their “we support (mostly) macOS” stance.

Reminds me a bit about the good (bad?) old days of Apple vs. Microsoft. Who will win this time around? (Not that I care about the winning or the losing of one over the other, but I do find these different strategies interesting …)

#Edge #Browser #Microsoft #Apple