Machine Learning
- A diffusion model to colorize black and white imagesgithub.com GitHub - ErwannMillon/Color-diffusion: A diffusion model to colorize black and white images
A diffusion model to colorize black and white images - GitHub - ErwannMillon/Color-diffusion: A diffusion model to colorize black and white images
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorsguochengqian.github.io Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors, 2023.
- Containers for machine learninggithub.com GitHub - replicate/cog: Containers for machine learning
Containers for machine learning. Contribute to replicate/cog development by creating an account on GitHub.
- what are you reading this week ?
Hello Machine Learning Community,
The intention of this post is to replicate a similar tradition from R/machinelearning and to trigger engagement. This post will be created weekly.
What are you reading this week and any thoughts to share?
- RT-2: New model translates vision and language into actionwww.deepmind.com RT-2: New model translates vision and language into action
Introducing Robotic Transformer 2 (RT-2), a novel vision-language-action (VLA) model that learns from both web and robotics data, and translates this knowledge into generalised instructions for robotic control, while retaining web-scale capabilities. This work builds upon Robotic Transformer 1 (RT-1...
- what are you reading this week ?
Hello Machine Learning Community,
The intention of this post is to replicate a similar tradition from R/machinelearning and to trigger engagement. This post will be created weekly.
What are you reading this week and any thoughts to share?
- [Paper] Learning to Generate Better Than Your LLM
I was looking through papers that combine LLMs and RL and this was pretty fascinating and the citations are perfect for continuing my search.
- GitHub - aerdem4/lofo-importance: Leave One Feature Out Importancegithub.com GitHub - aerdem4/lofo-importance: Leave One Feature Out Importance
Leave One Feature Out Importance. Contribute to aerdem4/lofo-importance development by creating an account on GitHub.
- Almost All Research on the Mind is in English. That May Be a Problemwww.wired.com Almost All Research on the Mind Is in English. That’s a Problem
Language can shape how you think in subtle and profound ways. But most researchers only study English speakers.
- what are you reading this week ?
Hello Machine Learning Community,
The intention of this post is to replicate a similar tradition from R/machinelearning and to trigger engagement. This post will be created weekly.
What are you reading this week and any thought to share on it ?
- GPT-4's details are leakedpastebin.com Pastebin.com - Not Found (#404)
Pastebin.com is the number one paste tool since 2002. Pastebin is a website where you can store text online for a set period of time.
- what do you all think about a weekly "what are you reading ?" post ?
I'd love to know what others are reading, why they think it's awesome (or not). In general, get an exposure to other sub genres of ML. Most of the papers I read are in the computer vision domain cause of work so I'd appreciate reading more about others.
So...
- Are you all interested in such a post ?
- If yes, which day of the week ?
- Gaussian processes from scratchpeterroelants.github.io Gaussian processes (1/3) - From scratch
This post explores some concepts behind Gaussian processes, such as stochastic processes and the kernel function. We will build up deeper understanding of Gaussian process regression by implementing them from scratch using Python and NumPy.
- Great series by Andrej Karpathy on machine learning and training
Great series on machine learning. Posting for anyone interested in more of the details on the AI's and LLM's and how they're built/trained.
- SDXL Model Reportgithub.com File not found · Stability-AI/generative-models
Generative Models by Stability AI. Contribute to Stability-AI/generative-models development by creating an account on GitHub.
TLDR of Stability-AI's Paper:
Summary: The document discusses the advancements and limitations of the Stable Diffusion (SDXL) model for text-to-image synthesis. SDXL shows significant improvements in synthesized image quality, prompt adherence, and composition. However, it also has limitations such as challenges in synthesizing intricate structures like human hands, achieving perfect photorealism, addressing biases, mitigating concept bleeding, and improving text rendering. The document also compares SDXL with Midjourney v5.1, where SDXL shows a slight preference in terms of prompt adherence. The document concludes with suggestions for future improvements.
Key Takeaways:
- SDXL outperforms or is statistically equal to Midjourney V5.1 in 7 out of 10 categories.
- SDXL does not achieve better FID scores than the previous SD versions. This suggests the need for additional quantitative performance scores, specifically for text-to-image foundation models.
- SDXL outperforms Midjourney V5.1 in all but two categories in the user preference comparison.
- The model may encounter challenges when synthesizing intricate structures, such as human hands.
- The model does not attain perfect photorealism. Certain nuances, such as subtle lighting effects or minute texture variations, may still be absent or less faithfully represented in the generated images.
- The model’s training process heavily relies on large-scale datasets, which can inadvertently introduce social and racial biases.
- The model may exhibit a phenomenon known as “concept bleeding” where distinct visual elements unintentionally merge or overlap.
- The model encounters difficulties when rendering long, legible text.
- Future work should investigate ways to provide a single stage of equal or better quality, improve text synthesis, enable scaling to much larger transformer-dominated architectures, decrease the compute needed for inference, and increase sampling speed.
- AI makes non-invasive mind-reading possible by turning thoughts into textamp.theguardian.com AI makes non-invasive mind-reading possible by turning thoughts into text | Artificial intelligence (AI) | The Guardian
Advance raises prospect of new ways to restore speech in those struggling to communicate due to stroke or motor neurone disease
- Why Are There No Consumer Server GPUs?
I work with machine learning tasks daily, both as an ML researcher and as a hobby. The difference between what I can do at work and at home is significant - an A40 at work can do far more than the 3080 I have at home. This obviously makes sense, given the massively increased price point.
However, what I find odd is how there are no consumer level server GPUs targeted towards ML on the market. The A40 is not just a scaled up consumer GPU, and with machine learning growing as a hobby, consumer and enthusiast-level server GPUs are a surprising market gap.
- IBM Watson machine learning stopped development at PyTorch 1.7
https://public.dhe.ibm.com/ibmdl/export/pub/software/server/ibm-ai/conda/#/
On the face of it, the ability to run models larger than GPU memory would seem to be extremely valuable. Why did they give up? Not everyone has an 80GB GPU.
Was the performance too slow?
- New study shows that existing open-sourced LLMs often do not perform well in the claimed context-lengthlmsys.org How Long Can Open-Source LLMs Truly Promise on Context Length? | LMSYS Org
<p>In this blogpost, we introduce our latest series of chatbot models, LongChat-7B and LongChat-13B, featuring a new level of extended context length up to 1...</p>
- open orca dataset by ehartfordhuggingface.co 404 – Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
From the
README.md
:``` This is the real release of the open-orca dataset.
alpaca format, uncensored. ```
Original paper from ms research: https://arxiv.org/abs/2306.02707
Hartford's blog post detailing his work: https://erichartford.com/openorca
Grab the data and get to work: https://huggingface.co/datasets/OpenOrca/open-orca
- Vicuna 13B vs 33B
Hi! I posted this over at lemmy.world in the technology sublemmy, but I thought maybe some knowledgeable people here could answer the question easier.
Oh and I know it's not really designed to give out functioning code, but it does look good enough I thought I'd ask.
I have both Vicuna-13B and the preview version of Vicuna-33B running on my desktop and asked both a simple coding question from another user:
"What can I use to draw curved text in an SVG?"
I got these two answers, I am not really a code but, while the code looks like it could work, I don't think it is correct?
Can someone here tell me if either answer is correct or more correct than the other?
Thanks!
33B:
.....
User: How are you doing today?
Vicky: Today, I'm doing well, thank you for asking! How about you?
User: I am doing great! what can I use to draw curved text in an SVG?
Vicky: To draw curved text in an SVG, you can use the <textPath> element. This allows you to wrap text along a path defined by an SVG path or elliptical arc. First, create the path using the 'path' or 'ellipse' element, then use the <textPath> element to wrap the text along the path. Here's an example:
+++
html <svg xmlns="http://www.w3.org/2000/svg" width="800" height="600" viewBox="0 0 800 600"> <path id="curve" d="M200,200 Q400,200 400,400" fill="none" stroke="black" stroke-width="2"/> <text text-anchor="middle" dominant-baseline="central" x="300" y="300" text-path="url(#curve)"> The quick brown fox jumps over the lazy dog </text> </svg>
+++
In this example, a quadratic curve is defined using the 'Q' command in the 'path' element, and the text is wrapped along the curve using the <textPath> element with the 'url(#curve)' attribute. You can adjust the 'd' attribute of the path and the text's position to create different curves with the text. .....
13B:
.....
User: what can I use to draw curved text in an SVG?
Vicky: In SVG, you can use the "textPath" element to create curved text. You can also use the "text" element and position it using "transform" attributes to achieve the same effect.
User:Can you give me a code example for that?
Vicky: Sure! Here's an example using the "textPath" element:
+++
php <svg width="100" height="100"> <text xlink:href="#text1" y="50" text-anchor="middle" font-size="20"> This text has a curved path. </text> <rect x="50" y="50" width="30" height="10" fill="#000" /> <text xlink:href="#text2" x="70" y="50" text-anchor="middle" font-size="20"> This text has a curved path. </text> </svg>
+++
And here's an example using the "text" element:
+++
php <svg width="100" height="100"> <text xlink:href="#text1" y="50" text-anchor="middle" font-size="20"> This text has a curved path. </text> <rect x="50" y="50" width="30" height="10" fill="#000" /> <text x="70" y="50" text-anchor="middle" font-size="20"> This text has a curved path. </text> </svg>
+++
*Note that you'll need to define the curved path for each text element using an SVG path string. In this case, the path strings are
#text1
and#text2
.To use the same path for multiple text elements, you can define the path once and then reference it using the
xlink:href
attribute. Thetext-anchor
attribute determines the point of the text element where the path is anchored.*.....
(no idea why Lemmy doesn't italicize that last text part)
13B-Vicky gave more code, no idea which code example is better. 13B runs much faster than 33B, it would be really interesting to know if either or both example codes are valid and if 13B, despite being the simpler model gave a correct answer. 33B is a preview model not the final version.
What I am noticing is that neither has actually used the textPath element, though 33B used text-path, no idea if that exists.
p.s. by offloading 41 of the 63 layers to gpu 33B runs as fast as 13B without offloading but with CUDA on my machine. Very interesting.
- Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shiftopenreview.net Reversible Instance Normalization for Accurate Time-Series...
Statistical properties such as mean and variance often change over time in time series, i.e., time-series data suffer from a distribution shift problem. This change in temporal distribution is one...
I found this paper when implementing TSMixer in darts and thought it was worth sharing.
As far as I know, it may not be relevant to non-timeseries problems. That being said, does anybody know of instance normalization outside of timeseries? It is obviously similar to batch normalization but is slightly different.
I added RIN to an N-HiTS model using the Energy benchmark dataset and got 21% and 22% reduction in MSE and MAE, respectively. This required two lines of code to be added to the model definition and increased compute time in no noticeable manner.
- Machine Learning books recommendations?
I'm trying to learning machine learning from a more mathematical/theory side of machine learning just so its easier for me to understand AI/ML papers that are coming out just to keep up with them. I would say that I have a basic understanding of AI/ML but more so on the applied side like in Keras, TF, PyTorch somewhat but I feel like I am lacking on my understanding on the mathematical side of AI/ML. So any books and course recs for that?
- The bigger-is-better approach to AI is running out of roadwww.economist.com The bigger-is-better approach to AI is running out of road
If AI is to keep getting better, it will have to do more with less
- Stability AI launches SDXL 0.9: A Leap Forward in AI Image Generationstability.ai Stability AI launches SDXL 0.9: A Leap Forward in AI Image Generation — Stability AI
Discover SDXL 0.9, Stability AI's cutting-edge release in the Stable Diffusion suite. Unleashing remarkable image and composition precision, this upgrade revolutionizes generative AI imagery. From hyper-realistic media production to design and industrial advancements, explore the limitless possibili
- Emerging Architectures for LLM Applicationsa16z.com Emerging Architectures for LLM Applications | Andreessen Horowitz
A reference architecture for the LLM app stack. It shows the most common systems, tools, and design patterns used by AI startups and tech companies.
- Adaptive Resonance Theory vs Backpropagation-based Machine Learning
In recent weeks, I came across Adaptive Resonance Theory that attempts to solve similar problems to what the mainstream backpropagation based machine learning and deep learning attempt to solve. There's also a 2017 paper on DeepART. The interesting part is the claim that ART overcomes much of the problems associated with backpropagation. Inspite of this, in my experience of the last 5 years of seeing machine learning, I've seen backpropagation much more and almost never seen adaptive resonance theory, and google trends seems to agree with my experience.
So, are there inherent problems that adaptive resonance theory does not solve, for which backpropagation-based machine learning has worked out pretty well? Or is it just another coincidence in the tech industry for why something won out in favour of something else?
- Researchers have created a small device that ‘sees’ and creates memories in a similar way to humans.www.rmit.edu.au Tiny device mimics human vision and memory abilities
Researchers have created a small device that ‘sees’ and creates memories in a similar way to humans, in a step towards autonomous decision making.
- QR Code AI Art Generatorhuggingface.co QR Code AI Art Generator - a Hugging Face Space by huggingface-projects
Discover amazing ML apps made by the community
- Meta AI -- I-JEPA: The first AI model based on Yann LeCun’s vision for more human-like AIai.facebook.com I-JEPA: The first AI model based on Yann LeCun’s vision for more human-like AI
I-JEPA learns by creating an internal model of the outside world, which compares abstract representations of images (rather than comparing the pixels themselves).
- Native JSON Output From GPT-4yonom.substack.com Native JSON Output From GPT-4
When integrating LLMs in your products, you often want to generate structured data, like JSONs. With the help of function calling (released June 13th 2023), this process has become much simpler! In this post I will explore the new API. Thanks for reading Simon’s Substack! Subscribe for free to recei...
- New model offers a way to speed up drug discoverynews.mit.edu New model offers a way to speed up drug discovery
A model known as ConPLex can predict whether potential drug molecules will interact with specific protein targets, without having to perform the computationally intensive calculation of the molecules’ structures.
Very cool application of LLM to screen potential protein-drug interactions.
- A Gentle Introduction to Graph Neural Networksdistill.pub A Gentle Introduction to Graph Neural Networks
What components are needed for building learning algorithms that leverage the structure and properties of graphs?