We present an approach to denoising spatial transcriptomics images that is particularly effective for uncovering cell identities in the regime of ultra-low sequencing depths, and also allows for interpolation of gene expression. The method -- Spatial Transcriptomics via Adaptive Regularization and Kernels (STARK) -- augments kernel ridge regression with an incrementally adaptive graph Laplacian regularizer. In each iteration, we (1) perform kernel ridge regression with a fixed graph to update the image, and (2) update the graph based on the new image. The kernel ridge regression step involves reducing the infinite dimensional problem on a space of images to finite dimensions via a modified representer theorem. Starting with a purely spatial graph, and updating it as we improve our image makes the graph more robust to noise in low sequencing depth regimes. We show that the aforementioned approach optimizes a block-convex objective through an alternating minimization scheme wherein the sub-problems have closed form expressions that are easily computed. This perspective allows us to prove convergence of the iterates to a stationary point of this non-convex objective. Statistically, such stationary points converge to the ground truth with rate $\mathcal{O}(R^{-1/2})$ where $R$ is the number of reads. In numerical experiments on real spatial transcriptomics data, the denoising performance of STARK, evaluated in terms of label transfer accuracy, shows consistent improvement over the competing methods tested.

Analyzing spoken discourse is a valid means of quantifying language ability in persons with aphasia. There are many ways to quantify discourse, one common way being to evaluate the informativeness of the discourse. That is, given the total number of words produced, how many of those are context-relevant and accurate. This type of analysis is called Correct Information Unit (CIU) analysis and is one of the most prevalent discourse analyses used by speech-language pathologists (SLPs). Despite this, CIU analysis in the clinic remains limited due to the manual labor needed by SLPs to code and analyze collected speech. Recent advances in machine learning (ML) seek to augment such labor by automating modeling of propositional, macrostructural, pragmatic, and multimodal dimensions of discourse. To that end, this study evaluated five ML models for reliable identification of Correct Information Units (CIUs, Nicholas & Brookshire, 1993), during a picture description task. The five supervised ML models were trained using randomly selected human-coded transcripts and accompanying words and CIUs from persons with aphasia. The baseline model training produced a high accuracy across transcripts for word vs non-word, with all models achieving near perfect performance (0.995) with high AUC range (0.914 min, 0.995 max). In contrast, CIU vs non-CIU showed a greater variability, with the k-nearest neighbor (k-NN) model the highest accuracy (0.824) and second highest AUC (0.787). These findings indicate that while the supervised ML models can distinguish word from not word, identifying CIUs is challenging.

The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory hierarchies, thread scheduling, and hardware-specific characteristics. While recent advances in large language models (LLMs) provide new opportunities for automated code generation, existing approaches largely treat LLMs as single-shot generators or naive refinement tools, limiting their effectiveness in navigating the irregular kernel optimization landscape. We introduce an LLM agentic framework for GPU kernel optimization that systematically explores the design space through multi-agent collaboration, grounded instruction, dynamic context management, and strategic search. This framework mimics the workflow of expert engineers, enabling LLMs to reason about hardware trade-offs, incorporate profiling feedback, and refine kernels iteratively. We evaluate our approach on KernelBench, a benchmark for LLM-based kernel optimization, and demonstrate substantial improvements over baseline agents: our system produces correct solutions where baselines often fail, and achieves kernels with up to 16x faster runtime performance. These results highlight the potential of agentic LLM frameworks to advance fully automated, scalable GPU kernel optimization.

There's arguably no face, voice or collection of exuberant, patterned shirts more recognisable than those belonging to Dr Karl Kruszelnicki. The bespectacled boffin has been answering curly listener questions about science, with characteristic excitement and passion, for more than 40 years. Despite a seemingly tireless work ethic, Kruszelnicki, now 77 years old, can't be everywhere all at once. Those questions now come in waves, across social media platforms at all hours of the day. "Sometimes I get 300 requests a day on Twitter to answer an involved question about climate change," Kruszelnicki says.

Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity relations of products) information. However, many previous works studied textual and relational retrieval tasks as separate topics. To address the gap, we develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Relational Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in precision medicine. We design a novel pipeline to synthesize realistic user queries that integrate diverse relational information and complex textual properties, together with their ground-truth answers (items).

We consider standard gradient descent, gradient flow and conjugate gradients as iterative algorithms for minimizing a penalized ridge criterion in linear regression. While it is well known that conjugate gradients exhibit fast numerical convergence, the statistical properties of their iterates are more difficult to assess due to inherent nonlinearities and dependencies. On the other hand, standard gradient flow is a linear method with well known regularizing properties when stopped early. By an explicit non-standard error decomposition we are able to bound the prediction error for conjugate gradient iterates by a corresponding prediction error of gradient flow at transformed iteration indices. This way, the risk along the entire regularisation path of conjugate gradient iterations can be compared to that for regularisation paths of standard linear methods like gradient flow and ridge regression. In particular, the oracle conjugate gradient iterate shares the optimality properties of the gradient flow and ridge regression oracles up to a constant factor. Numerical examples show the similarity of the regularisation paths in practice.

WHAT-IF--Writing a Hero's Alternate Timeline through Interactive Fiction--is a system that uses zero-shot meta-prompting to create branching narratives from a prewritten story. Played as an interactive fiction (IF) game, WHAT-IF lets the player choose between decisions that the large language model (LLM) GPT-4 generates as possible branches in the story. Starting with an existing linear plot as input, a branch is created at each key decision taken by the main character. By meta-prompting the LLM to consider the major plot points from the story, the system produces coherent and well-structured alternate storylines. WHAT-IF stores the branching plot tree in a graph which helps it to both keep track of the story for prompting and maintain the structure for the final IF system. Figure 1: The WHAT-IF user interface, filled with the A video demo of our system can be found here: main character, title, and the plot of the TV show WandaVision https://youtu.be/8vBqjqtupcc.

ChatGPT, Bing Chat, and Bard promise to transform your life using the power of artificial intelligence, through AI conversations that can inform, amuse, and educate you--just like a human being. But how good are these new AI chatbots, really? We tested them to find out. We asked all three AIs a variety of different questions: some that expanded upon general search topics, some that demanded an opinion, logic puzzles, even code--and then asked them to be more creative, such as by writing an alternate, better ending to Game of Thrones and a Seinfeld scene with a special guest. We've included all of their answers, or as much as them as we could provide, and we'll let you decide for yourself.

In November 2021, Facebook announced it would delete face recognition data extracted from images of more than 1 billion people and stop offering to automatically tag people in photos and videos. Luke Stark, an assistant professor at Western University, in Canada, told WIRED at the time that he considered the policy change a PR tactic because the company's VR push would likely lead to the expanded collection of physiological data and raise new privacy concerns. This week, Stark's prediction proved right. Meta, as the company that built Facebook is now called, introduced its latest VR headset, the Quest Pro. The new model adds a set of five inward-facing cameras that watch a person's face to track eye movements and facial expressions, allowing an avatar to reflect their expressions, smiling, winking, or raising an eyebrow in real time.