"AI Chat Assistants can Improve Conversations about Divisive Topics" — A study looking at how Large Language Models can improve conversations on divisive topics by making the participants feel understood.

Paper: https://arxiv.org/abs/2302.07268

#AI #NewPaper #DeepLearning #MachineLearning #Language #HumanComputerInteraction
Treated Conversation Flow: Resp…

"CiteSee: Augmenting Citations in Scientific Papers with Persistent and Personalized Historical Context" — A tool that uses a reader’s publishing, reading, and saving history to provide personalised context to citations in papers that they’re reading.

Paper: https://arxiv.org/abs/2302.07302

#NewPaper #HumanComputerInteraction
CiteSee augments inline citatio…

"Augmenting Pathologists with NaviPath: Design and Evaluation of a Human-AI Collaborative Navigation System" — Using the navigation strategies of human pathologists to use their domain knowledge to enhance machine learning systems to navigate hight-resolution tumor images to search for patterns of interest.

Paper: https://arxiv.org/abs/2302.07309

#AI #NewPaper #DeepLearning #MachineLearning #HumanComputerInteraction

"Stitchable Neural Networks. (arXiv:2302.06586v2 [cs.LG] UPDATED)" — A way to combine different pretrained models to combine models of varying complexity and performance.

Paper: http://arxiv.org/abs/2302.06586

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Compared with previous scalable…

"Learning When to Say "I Don't Know". (arXiv:2209.04944v2 [cs.CV] UPDATED)" — A method to teach learning systems when they don't know something, or at least to identify areas of uncertainty. Perhaps this should be tried with ChatGPT and Bing to mitigate all the gaslighting? 😛

Paper: http://arxiv.org/abs/2209.04944
Code: https://github.com/osu-cvl/learning-idk

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
t-SNE plots of logits from a we…

"SoK: Anti-Facial Recognition Technology. (arXiv:2112.04558v2 [cs.CR] UPDATED)" — An analysis of the currently available Anti-Facial Recognition (AFR) research and the pros and cons of the different approaches.

Paper: http://arxiv.org/abs/2112.04558

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The workflow of how facial reco…

"Team Triple-Check at Factify 2: Parameter-Efficient Large Foundation Models with Feature Representations for Multi-Modal Fact Verification. (arXiv:2302.07740v1 [cs.CL])" — Verifying facts across different modes (text and images) and types (claim and document).

Paper: http://arxiv.org/abs/2302.07740
Code: https://github.com/wwweiwei/Pre-CoFactv2-AAAI-2023

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
An example of each category in …

"Video Probabilistic Diffusion Models in Projected Latent Space. (arXiv:2302.07685v1 [cs.CV])" — Generating high-resolution and coherent video using diffusion models.

Paper: http://arxiv.org/abs/2302.07685

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
256×256 resolution, 128 frame v…

A total of 54 papers in the cs.CV category on arXiv.org today — 33 new, 21 updated.

Are we slowing down for the weekend? 😛

#AI #CV #NewPapers #DeepLearning #MachineLearning

I do most of my #StableDiffusion image generation using various scripts or GUIs that I created. Each of them store the image generation parameters in the image as meta data.

My latest generation GUI is also an image gallery. It lets me view the images I’ve generated and being able to see the parameters is handy since I can compare various images later and see what model, prompt, and settings were used.

I also do image generation on #Windows (as opposed to #Mac) using #InvokeAI. Now InovkeAI does store the generation settings in the image too but obviously, the keys used to store the data are different to mine.

So my image gallery does not show the settings used when I browse images generated in InokeAI 😛

I got a bunch of coding done and the new GUI working correctly as I liked yesterday. Now I have to figure out how to extract the metadata for InvokeAI-generated images and to display that in my viewer too … It never stops 😀

#Coding #ImageViewer #MachineLearning

Hey, folks. Big layoffs at DigitalOcean today, and my team and I were hit. In fact, so was my adjacent team, and a good chunk of my department. I don't have much reach here on Mastodon yet, but if anybody wants to discuss opportunities for a technical editor / writer / manager of same, I'm up for it.

@AngelaPreston I used to test myself all the time to see if I was good enough. I took it as a challenge. That’s how I think I got into quizzing. And puzzles. And the kind of game where you have to think about things instead of mashing buttons.

As far as work goes, I know that there are people better than me at what I do. So I do wonder if things can be done better, but most of the time, I think I do the best I can and don’t worry about it too much beyond that since there’s always something new over the next hill and I’ve forgotten about whatever I did today by tomorrow 😛

Anybody doing any #Generative #MachineLearning stuff and posting about it as you work on it? Not papers? But just the daily trials and tribulations (and successes) of working on stuff. Have too many #DeepLearning and #MachineLearning accounts talking about their courses and videos and stuff and not enough of the daily stuff …

I miss that … Seeing what other people are working on, the small triumphs, and learning about new ways to do/try things …

If you are out there, hit me up and I’d like to follow you 🙂

@ajyoung Sorry, was asleep and woke up only now 🙂

I don’t generally generate using Python (I use my own GUI) but the issue is probably here “-o <creations/>” … If you change that to “-o creations” (assuming that you have a sub-folder named “creations” where you’re running the command from) it should work…

Let me know if it doesn’t and we can try to figure it out from there …

I'm excited to be presenting a tutorial for new programmers at @pycon this year. 😊

Have a colleague attending #PyCon2022 who doesn't (yet) write code? 🧑‍💻

Ask them to keep an eye out for "Intro to Python for Brand New Programmers" when tutorial registration opens up! 💖

@ajyoung No bother, happy to help 🙂

Can you send me the command you ran? It looks as if the script was looking for input from the standard input (maybe) and got a folder maybe? Haveing the command you ran might give a bit more context perhaps ….

Yesterday's Pratchett novel title prompt was: "Snuff"

I didn't really expect much from that one since there isn't a lot to work with there. But I still got some interesting images 🙂

These are from multiple models and so the styles are a little different across images. But still, I thought the end results were interesting ...

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI #DiscWorld
Prompt: “Snuff”. Colourful pict…
Prompt: “Snuff”. A huge creatur…
Prompt: “Snuff”. A colourful im…
Prompt: “Snuff”. A colourful bu…

This photo was taken in Kenai, #Alaska yesterday next to the Senior Center and Senior Apartments overlooking Cook Inlet with the mountain range in the background. And of course, there is a kneeling moose eating some grub. This is the area of the state I live in. 💗
📸 by Carol Reinhardt King
#AlaskaMoose #Moosetodon

And with 11 papers boosted out of 82 in the cs.CV category on arXiv, we are done with papers for the day 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

"DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model. (arXiv:2302.06908v1 [cs.CV])" — Today seems to be the day for papers on turning sketches into realistic colour images using diffusion models 😛 This is another approach ...

Paper: http://arxiv.org/abs/2302.06908

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A Sketch-Guided Lantent Diffusi…