Accurately predicting protein fitness with minimal experimental data is a persistent challenge in protein engineering. We introduce PRIMO (PRotein In-context Mutation Oracle), a transformer-based framework that leverages in-context learning and test-time training to adapt rapidly to new proteins and assays without large task-specific datasets. By encoding sequence information, auxiliary zero-shot predictions, and sparse experimental labels from many assays as a unified token set in a pre-training masked-language modeling paradigm, PRIMO learns to prioritize promising variants through a preference-based loss function. Across diverse protein families and properties-including both substitution and indel mutations-PRIMO outperforms zero-shot and fully supervised baselines. This work underscores the power of combining large-scale pre-training with efficient test-time adaptation to tackle challenging protein design tasks where data collection is expensive and label availability is limited.

While Deep Learning (DL) experts often have prior knowledge about which hyperparameter settings yield strong performance, only few Hyperparameter Optimization (HPO) algorithms can leverage such prior knowledge and none incorporate priors over multiple objectives. As DL practitioners often need to optimize not just one but many objectives, this is a blind spot in the algorithmic landscape of HPO. To address this shortcoming, we introduce PriMO, the first HPO algorithm that can integrate multi-objective user beliefs. We show PriMO achieves state-of-the-art performance across 8 DL benchmarks in the multi-objective and single-objective setting, clearly positioning itself as the new go-to HPO algorithm for DL practitioners.

Open rule refer to the implication from premise atoms to hypothesis atoms, which captures various relations between instances in the real world. Injecting open rule knowledge into the machine helps to improve the performance of downstream tasks such as dialogue and relation extraction. Existing approaches focus on single-hop open rule generation, ignoring multi-hop scenarios, leading to logical inconsistencies between premise and hypothesis atoms, as well as semantic duplication of generated rule atoms. To address these issues, we propose a progressive multi-stage open rule generation method called PRIMO. We introduce ontology information during the rule generation stage to reduce ambiguity and improve rule accuracy. PRIMO constructs a multi-stage structure consisting of generation, extraction, and ranking modules to fully leverage the latent knowledge within the language model across multiple dimensions. Furthermore, we employ reinforcement learning from human feedback to further optimize model, enhancing the model's understanding of commonsense knowledge. Experiments show that compared to baseline models, PRIMO significantly improves rule quality and diversity while reducing the repetition rate of rule atoms.

Researchers have used machine learning to tighten up a previously released image of a black hole. As a result, the portrait of the black hole at the center of the galaxy Messier 87, over 53 million light years away from Earth, shows a thinner ring of light and matter surrounding its center in a report published today in The Astrophysical Journal Letters. The original images were captured in 2017 by the Event Horizon Telescope (EHT), a network of radio telescopes around Earth that combine to act as a planet-sized super-imaging tool. The initial picture looked like a "fuzzy donut," as described by NPR, but researchers used a new method called PRIMO to reconstruct a more accurate image. PRIMO is "a novel dictionary-learning-based algorithm" that learns to "recover high-fidelity images even in the presence of sparse coverage" by training on generated simulations of over 30,000 black holes.

The exceptional resolution achieved by the EHT is made possible by an array of telescopes spanning the Earth and operating as a very long baseline interferometer (VLBI; Event Horizon Telescope Collaboration et al. 2019b, 2019c). Despite this global reach, the sparse interferometric coverage of the EHT array (especially during the 2017 observations that have been used for all of the publications to date) makes the already complex problem of interferometric image reconstruction particularly challenging. In such situations, special care is needed to assess the impact of imaging algorithms and sparse interferometric data on the final set of images that can be reconstructed from it. A cornerstone of the EHT data analysis strategy was the use of several independent analysis methods, each with different priorities, assumptions, and choices, to ensure that the EHT results were robust to these differences. The use of several general-purpose imaging algorithms, for example, was motivated by a desire to reconstruct an image that was consistent with the EHT data while remaining model-agnostic.

It is a thing of mesmerising beauty: humanity's first glimpse at the only full resolution photo of a supermassive black hole ever produced. This'orange donut', as it has been dubbed, sits at the heart of the Messier 87 galaxy 55 million light-years from Earth and in 2019 became the first black hole to be directly imaged by astronomers. Now, with the help of artificial intelligence (AI) machine learning, it has received its first official makeover -- and the results reveal that rather than being a'fuzzy donut', it is actually more of a'skinny donut'. Scientists say this new perspective of the supermassive black hole will'play a critical role in our ability to understand its behaviour' and could help explain how the stellar phenomenon'eats' matter. They called it a'golden opportunity' to learn more about black hole physics.

We introduce a new differentially private regression setting we call Private Regression in Multiple Outcomes (PRIMO), inspired the common situation where a data analyst wants to perform a set of $l$ regressions while preserving privacy, where the covariates $X$ are shared across all $l$ regressions, and each regression $i \in [l]$ has a different vector of outcomes $y_i$. While naively applying private linear regression techniques $l$ times leads to a $\sqrt{l}$ multiplicative increase in error over the standard linear regression setting, in Subsection $4.1$ we modify techniques based on sufficient statistics perturbation (SSP) to yield greatly improved dependence on $l$. In Subsection $4.2$ we prove an equivalence to the problem of privately releasing the answers to a special class of low-sensitivity queries we call inner product queries. Via this equivalence, we adapt the geometric projection-based methods from prior work on private query release to the PRIMO setting. Under the assumption the labels $Y$ are public, the projection gives improved results over the Gaussian mechanism when $n < l\sqrt{d}$, with no asymptotic dependence on $l$ in the error. In Subsection $4.3$ we study the complexity of our projection algorithm, and analyze a faster sub-sampling based variant in Subsection $4.4$. Finally in Section $5$ we apply our algorithms to the task of private genomic risk prediction for multiple phenotypes using data from the 1000 Genomes project. We find that for moderately large values of $l$ our techniques drastically improve the accuracy relative to both the naive baseline that uses existing private regression methods and our modified SSP algorithm that doesn't use the projection.

A major difficulty in developing and maintaining very large knowledge bases originates from the variety of forms in which knowledge is made available to the KB builder. The objective of this research is to bring together two complementary knowledge representation schemes: term subsumption languages, which represent and reason about defining characteristics of concepts, and proximate reasoning models, which deal with uncertain knowledge and data in expert systems. Previous works in this area have primarily focused on probabilistic inheritance. In this paper, we address two other important issues regarding the integration of term subsumption-based systems and approximate reasoning models. First, we outline a general architecture that specifies the interactions between the deductive reasoner of a term subsumption system and an approximate reasoner. Second, we generalize the semantics of terminological language so that terminological knowledge can be used to make plausible inferences. The architecture, combined with the generalized semantics, forms the foundation of a synergistic tight integration of term subsumption systems and approximate reasoning models.