World's longest tiramisu record broken in London The record for the world's longest tiramisu has been broken in London. One-hundred Italian chefs gathered at Chelsea Town Hall on Saturday and Sunday to whip up a tiramisu long enough to topple the previous record set by Milanese Galbani in Milan, which stood at 273.5m (897ft). As per Guinness World Record rules, the record-breaking tiramisu was made and assembled live on site, and used 50,000 ladyfinger biscuits and more than 3,000 eggs. The record was broken with the dessert measuring 440.6 m (1,445ft). Mirko Ricci, the man behind the London record attempt, originally held the record in 2017 in Italy, but another Italian team broke that in 2019.

This position paper argues that, in order to understand AI, we cannot rely on our existing vocabulary of human words. Instead, we should strive to develop neologisms: new words that represent precise human concepts that we want to teach machines, or machine concepts that we need to learn. We start from the premise that humans and machines have differing concepts. This means interpretability can be framed as a communication problem: humans must be able to reference and control machine concepts, and communicate human concepts to machines. Creating a shared human-machine language through developing neologisms, we believe, could solve this communication problem. Successful neologisms achieve a useful amount of abstraction: not too detailed, so they're reusable in many contexts, and not too high-level, so they convey precise information. As a proof of concept, we demonstrate how a "length neologism" enables controlling LLM response length, while a "diversity neologism" allows sampling more variable responses. Taken together, we argue that we cannot understand AI using our existing vocabulary, and expanding it through neologisms creates opportunities for both controlling and understanding machines better.

Performance models are essential for automatic code optimization, enabling compilers to predict the effects of code transformations on performance and guide search for optimal transformations. Building state-of-the-art performance models with deep learning, however, requires vast labeled datasets of random programs -- an expensive and time-consuming process, stretching over months. This paper introduces a self-supervised pre-training scheme with autoencoders to reduce the need for labeled data. By pre-training on a large dataset of random programs, the autoencoder learns representations of code and transformations, which are then used to embed programs for the performance model. Implemented in the Tiramisu autoscheduler, our approach improves model accuracy with less data. For example, to achieve a MAPE of 20.72%, the original model requires 18 million data points, whereas our method achieves a similar MAPE of 22.44% with only 3.6 million data points, reducing data requirements by 5x.

Diffusion models are the current state of the art for generating photorealistic images. Controlling the sampling process for constrained image generation tasks such as inpainting, however, remains challenging since exact conditioning on such constraints is intractable. While existing methods use various techniques to approximate the constrained posterior, this paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior, and to leverage this signal to steer the denoising process of diffusion models. Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs). Building upon prior advances, we further scale up PCs and make them capable of guiding the image generation process of diffusion models. Empirical results suggest that our approach can consistently improve the overall quality and semantic coherence of inpainted images across three natural image datasets (i.e., CelebA-HQ, ImageNet, and LSUN) with only ~10% additional computational overhead brought by the TPM. Further, with the help of an image encoder and decoder, our method can readily accept semantic constraints on specific regions of the image, which opens up the potential for more controlled image generation tasks. In addition to proposing a new framework for constrained image generation, this paper highlights the benefit of more tractable models and motivates the development of expressive TPMs.

This post describes our work and research on the greenScreen.AI. We'll be happy to hear thoughts and comments -On Twitter, Linkedin Throughout the last few years in machine learning, I've always wanted to build real machine learning products. A few months ago, after taking the great Fast.AI deep learning course, it seemed like the stars aligned, and I have the opportunity: The advances in deep learning technology permitted doing many things that weren't possible before, and new tools were developed and made the deployment process more accessible than ever. In the aforementioned course, I've met Alon Burg, who is an experienced web developer, an we've partnered up to pursue this goal. Together, we've set ourselves the following goals: Our early thoughts were to take on some medical project, since this field is very close to our hearts, and we felt (and still feel) that there is an enormous number of low hanging fruits for deep learning in the medical field.

Throughout the last few years in machine learning, I've always wanted to build real machine learning products. A few months ago, after taking the great Fast.AI deep learning course, it seemed like the stars aligned, and I have the opportunity: The advances in deep learning technology permitted doing many things that weren't possible before, and new tools were developed and made the deployment process more accessible than ever. In the aforementioned course, I've met Alon Burg, who is an experienced web developer, an we've partnered up to pursue this goal. Together, we've set ourselves the following goals: Our early thoughts were to take on some medical project, since this field is very close to our hearts, and we felt (and still feel) that there is an enormous number of low hanging fruits for deep learning in the medical field. However, we realized that we are going to stumble upon issues with data collection and perhaps legality and regulation, which was a contradiction with our will to keep it simple.