A critical target scenario is high-throughput screening for scientific discovery, such as drug or materials discovery.

The advantage of the DAG formalism comes at generation time.

We study online inverse linear optimization, also known as contextual recommendation, where a learner sequentially infers an agent's hidden objective vector from observed optimal actions over feasible sets that change over time. The learner aims to recommend actions that perform well under the agent's true objective, and the performance is measured by the regret, defined as the cumulative gap between the agent's optimal values and those achieved by the learner's recommended actions. Prior work has established a regret bound of $O(d\log T)$, as well as a finite but exponentially large bound of $\exp(O(d\log d))$, where $d$ is the dimension of the optimization problem and $T$ is the time horizon, while a regret lower bound of $Ω(d)$ is known (Gollapudi et al. 2021; Sakaue et al. 2025). Whether a finite regret bound polynomial in $d$ is achievable or not has remained an open question. We partially resolve this by showing that when the feasible sets are M-convex -- a broad class that includes matroids -- a finite regret bound of $O(d\log d)$ is possible. We achieve this by combining a structural characterization of optimal solutions on M-convex sets with a geometric volume argument. Moreover, we extend our approach to adversarially corrupted feedback in up to $C$ rounds. We obtain a regret bound of $O((C+1)d\log d)$ without prior knowledge of $C$, by monitoring directed graphs induced by the observed feedback to detect corruptions adaptively.

Why Experts Can't Agree on Whether AI Has a Mind Pillay is an editorial fellow at TIME. Pillay is an editorial fellow at TIME. I'm not used to getting nasty emails from a holy man, says Professor Michael Levin, a developmental biologist at Tufts University. Levin was presenting his research to a group of engineers interested in spiritual matters in India, arguing that properties like "mind" and intelligence can be observed even in cellular systems, and that they exist on a spectrum. But when he pushed further--arguing that the same properties emerge everywhere, including in computers--the reception shifted.

Sparse Autoencoders (SAEs) can efficiently identify candidate monosemantic features from pretrained neural networks for galaxy morphology. We demonstrate this on Euclid Q1 images using both supervised (Zoobot) and new self-supervised (MAE) models. Our publicly released MAE achieves superhuman image reconstruction performance. While a Principal Component Analysis (PCA) on the supervised model primarily identifies features already aligned with the Galaxy Zoo decision tree, SAEs can identify interpretable features outside of this framework. SAE features also show stronger alignment than PCA with Galaxy Zoo labels. Although challenges in interpretability remain, SAEs provide a powerful engine for discovering astrophysical phenomena beyond the confines of human-defined classification.

Many real world tasks where Large Language Models (LLMs) can be used require spatial reasoning, like Point of Interest (POI) recommendation and itinerary planning. However, on their own LLMs lack reliable spatial reasoning capabilities, especially about distances. To address this problem, we develop a novel approach, DistRAG, that enables an LLM to retrieve relevant spatial information not explicitly learned during training. Our method encodes the geodesic distances between cities and towns in a graph and retrieves a context subgraph relevant to the question. Using this technique, our method enables an LLM to answer distance-based reasoning questions that it otherwise cannot answer. Given the vast array of possible places an LLM could be asked about, DistRAG offers a flexible first step towards providing a rudimentary `world model' to complement the linguistic knowledge held in LLMs.

This paper explores the idea of using phonemes as a textual representation within a conventional multilingual simultaneous speech - to - speech translation pipeline, as opposed to the traditional reliance on text - based language representations. To investigate this, we trained an open - source sequence - to - sequence model on the WMT17 dataset in two formats: one using standard textual representation and the other employing phonemic representation. The performance o f both approaches was assessed using the BLEU metric. Our findings shows that the phonemic approach provides comparable quality but offers several advantages, including lower resource requirements or better suitability for low - resource languages.

Autoregressive language models like GPT aim at predicting next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder only architecture for predicting the second last token for a sequence of tokens. Our approach yields higher computational training efficiency than BERT-style models by employing a structured deterministic approach towards masking tokens. We use our model to improve the next token predictions of a standard GPT by combining both predictions in a ``generate-then-refine'' approach. We show on different variants of GPT-2 and different datasets that (not unexpectedly) second last token predictions are much more accurate, i.e., more than 15\% higher accuracy than ordinary next token predictors. The ``generate-then-refine'' approach also demonstrates notable improvements in next-token predictions, yielding smaller yet consistent and significant gains.

John Schneider tells Fox News Digital that he isn't afraid of artificial intelligence because it can't replicate the "heart" or the "soul." "What AI does not have and what AI cannot simulate is a heart, is a soul. So, I'm not afraid of AI," he told Fox News Digital. Schneider gave an analogy, comparing the technology to artificial dairy coffee creamer, to explain why he's not concerned. "A lot of people are talking about AI like it's this terrible, terrible thing that's coming in. I think it's powdered cream at best," he said.