Training large language models (LLMs) models directly in low-precision offers a way to address computational costs by improving both throughput and energy efficiency.

Machine learning in neurosurgery is limited by challenges in assembling large, high-quality imaging datasets. Synthetic data offers a scalable, privacy-preserving solution. We evaluated the feasibility of generating realistic lateral cervical spine radiographs using a denoising diffusion probabilistic model (DDPM) trained on 4,963 images from the Cervical Spine X-ray Atlas. Model performance was monitored via training/validation loss and Frechet inception distance, and synthetic image quality was assessed in a blinded "clinical Turing test" with six neuroradiologists and two spine-fellowship trained neurosurgeons. Experts reviewed 50 quartets containing one real and three synthetic images, identifying the real image and rating realism on a 4-point Likert scale. Experts correctly identified the real image in 29% of trials (Fleiss' kappa=0.061). Mean realism scores were comparable between real (3.323) and synthetic images (3.228, 3.258, and 3.320; p=0.383, 0.471, 1.000). Nearest-neighbor analysis found no evidence of memorization. We also provide a dataset of 20,063 synthetic radiographs. These results demonstrate that DDPM-generated cervical spine X-rays are statistically indistinguishable in realism and quality from real clinical images, offering a novel approach to creating large-scale neuroimaging datasets for ML applications in landmarking, segmentation, and classification.

How a single fertilized cell gives rise to a complex array of specialized cell types in development is a central question in biology. The cells grow, divide, and acquire differentiated characteristics through poorly understood molecular processes. A key approach to studying developmental processes is to infer the tree graph of cell lineage division and differentiation histories, providing an analytical framework for dissecting individual cells' molecular decisions during replication and differentiation. Although genetically engineered lineage-tracing methods have advanced the field, they are either infeasible or ethically constrained in many organisms. In contrast, modern single-cell technologies can measure high-content molecular profiles (e.g., transcriptomes) in a wide range of biological systems. Here, we introduce CellTreeQM, a novel deep learning method based on transformer architectures that learns an embedding space with geometric properties optimized for tree-graph inference. By formulating lineage reconstruction as a tree-metric learning problem, we have systematically explored supervised, weakly supervised, and unsupervised training settings and present a Lineage Reconstruction Benchmark to facilitate comprehensive evaluation of our learning method. We benchmarked the method on (1) synthetic data modeled via Brownian motion with independent noise and spurious signals and (2) lineage-resolved single-cell RNA sequencing datasets. Experimental results show that CellTreeQM recovers lineage structures with minimal supervision and limited data, offering a scalable framework for uncovering cell lineage relationships in challenging animal models. To our knowledge, this is the first method to cast cell lineage inference explicitly as a metric learning task, paving the way for future computational models aimed at uncovering the molecular dynamics of cell lineage.

Pattern images are everywhere in the digital and physical worlds, and tools to edit them are valuable. But editing pattern images is tricky: desired edits are often programmatic: structure-aware edits that alter the underlying program which generates the pattern. One could attempt to infer this underlying program, but current methods for doing so struggle with complex images and produce unorganized programs that make editing tedious. In this work, we introduce a novel approach to perform programmatic edits on pattern images. By using a pattern analogy -- a pair of simple patterns to demonstrate the intended edit -- and a learning-based generative model to execute these edits, our method allows users to intuitively edit patterns. To enable this paradigm, we introduce SplitWeave, a domain-specific language that, combined with a framework for sampling synthetic pattern analogies, enables the creation of a large, high-quality synthetic training dataset. We also present TriFuser, a Latent Diffusion Model (LDM) designed to overcome critical issues that arise when naively deploying LDMs to this task. Extensive experiments on real-world, artist-sourced patterns reveals that our method faithfully performs the demonstrated edit while also generalizing to related pattern styles beyond its training distribution.

We give a polynomial-time algorithm for provably learning the structure and parameters of bipartite noisy-or Bayesian networks of binary variables where the top layer is completely hidden. Unsupervised learning of these models is a form of discrete factor analysis, enabling the discovery of hidden variables and their causal relationships with observed data. We obtain an efficient learning algorithm for a family of Bayesian networks that we call quartet-learnable. For each latent variable, the existence of a singly-coupled quartet allows us to uniquely identify and learn all parameters involving that latent variable. We give a proof of the polynomial sample complexity of our learning algorithm, and experimentally compare it to variational EM.

We provide time- and sample-efficient algorithms for learning and testing latent-tree Ising models, i.e. Ising models that may only be observed at their leaf nodes. On the learning side, we obtain efficient algorithms for learning a tree-structured Ising model whose leaf node distribution is close in Total Variation Distance, improving on the results of prior work. On the testing side, we provide an efficient algorithm with fewer samples for testing whether two latent-tree Ising models have leaf-node distributions that are close or far in Total Variation distance. We obtain our algorithms by showing novel localization results for the total variation distance between the leaf-node distributions of tree-structured Ising models, in terms of their marginals on pairs of leaves.

A key assumption in multiple scientific applications is that the distribution of observed data can be modeled by a latent tree graphical model. An important example is phylogenetics, where the tree models the evolutionary lineages of various organisms. Given a set of independent realizations of the random variables at the leaves of the tree, a common task is to infer the underlying tree topology. In this work we develop Spectral Neighbor Joining (SNJ), a novel method to recover latent tree graphical models. In contrast to distance based methods, SNJ is based on a spectral measure of similarity between all pairs of observed variables. We prove that SNJ is consistent, and derive a sufficient condition for correct tree recovery from an estimated similarity matrix. Combining this condition with a concentration of measure result on the similarity matrix, we bound the number of samples required to recover the tree with high probability. We illustrate via extensive simulations that SNJ requires fewer samples to accurately recover trees in regimes where the tree contains a large number of leaves or long edges. We provide theoretical support for this observation by analyzing the model of a perfect binary tree.

It's no secret that Google and Microsoft are archrivals in the consumer and enterprise IT space. Think: search engines, productivity apps and email, infrastructure-as-a-service in the cloud, even news, tech-related and otherwise. Indeed, hospital executives following their moves throughout 2017 are also keenly aware that both titans turned their scopes toward healthcare more than ever before. What's more, they've been doing so in ways that only companies with R&D and M&A pockets billions of dollars deep can dream about. Google, for its part, plunked down $500 million to buy DeepMind in 2014 followed by Moodstocks in 2016, to name two.

The idea of storytelling is fascinating; to take an idea or an incident, and turn it into a story. It brings the idea to life and makes it more interesting. This happens in our day to day life. Whether we narrate a funny incident or our findings, stories have always been the "go-to" to draw interest from listeners and readers alike. For instance; when we talk of how one of our friends got scolded by a teacher, we tend to narrate the incident from the beginning so that a flow is maintained.

Inside an abandoned warehouse on the San Francisco docks, as the damp air floods through the holes in its rusted tin roof, Sunny Tang is playing her cello while recovering from the flu. She is 45 percent sad and 0.01 percent disgusted. That, at least, is the read from the AI that's tracking her expressions, gestures, and body language from the other side of the warehouse, flashing these stats on the movie screen behind her. The audience--several hundred people huddled between her and the AI, dressed in scarfs, hats, and overcoats--lets out a collective laugh. Tang is playing alongside the rest of the Kronos Quartet, the iconic San Francisco string ensemble known for its unorthodox experimentation, and the AI is obeying orders from Trevor Paglen, the American artist who poses big questions about technology and surveillance through nearly any medium he can get his hands on. It's all part of Sight Machine, a Paglen-orchestrated performance that explores the rise of computer vision.