AI for Science

Researchers used AlphaFold to identify how Cas proteins accommodate mismatched DNA targets, then redesigned key amino acids to reduce unwanted editing. The work points to a more targeted route for improving CRISPR safety.

The Trump administration’s first Genesis Mission grants put $5 billion behind AI-driven research. The controversy is less about using AI in science than about remaking public research around political control, private-sector logic, and measurable returns.

SciForma reframes scientific diagram generation around structural fidelity rather than surface-level visual plausibility. It decomposes correctness into components, arrows, and text, then trains models to satisfy all three at once.

A new benchmark, 3D-Fit, evaluates whether general-purpose LLMs can generate 3D ligands under realistic spatial constraints for structure-based drug design. The results suggest early promise, but also expose a clear gap versus specialized diffusion models.

A new benchmark shifts plasma diagnostic ML evaluation from clean sensor data to realistic failure conditions. The results show that sequence models can break down sharply when sensors fail near a disruption.

S1-Omni aims to reduce fragmentation in AI for Science by bringing diverse scientific data types into one reasoning model. It supports more than 200 scientific tasks and releases model weights, inference code, and a 10K-sample corpus subset.

The first three operational FireSat satellites have reached orbit, bringing a purpose-built wildfire detection constellation closer to service. Backed by Google and other funders, the system combines multispectral imaging with AI analysis to detect small fires earlier.

The paper introduces Mycelium, an active shared workspace designed to connect researchers and AI agents so that scientific observations and hypotheses can move to the people or systems able to act on them.

A new arXiv position paper argues that autoformalization should evolve from translating isolated statements into building complete, machine-checkable theory libraries.

SDABench shifts the evaluation of LLMs in scientific data analysis from workflow completion to the capabilities needed to support scientific claims.

A new arXiv paper introduces MOJO, a joint training framework that combines masked autoencoding with supervised decoding for spike-tokenizing neural models. The approach aims to make better use of unlabelled neural recordings, especially when behavioural labels are scarce.

A new arXiv paper tests whether frozen Evo 2 representations contain linearly accessible biosecurity-relevant information. Lightweight probes show strong performance on antimicrobial resistance detection, while virulence and generated-sequence labels remain more limited.

A new arXiv paper examines feature selection in renewable power prediction and proposes Cluster-based Sequential Feature Selection. CSFS matches the predictive performance of standard sequential feature selection while cutting computational cost by 21% on average.

A new arXiv paper extends empirical Bayes variational autoencoders to jointly model tumor growth, time to dropout, and genomic covariates. The work combines neural dynamics with semi-mechanistic pharmacometric structure.

A new arXiv paper introduces PlumeQuant, a diagnostic framework for checking whether methane plume masks, IME, plume length, emission rates and uncertainty estimates are internally consistent. The study shows that published scalar quantities often do not uniquely determine the plume boundary.

A new arXiv study proposes a two-step unsupervised clustering strategy for multimodal cardiac PET/MRI data. The method generates automated text and bullseye reports that align reasonably well with cardiac imaging specialists’ observations.

A new arXiv paper applies Quantum Kitchen Sinks to RF spectrogram anomaly detection using measured cellular signals and validation on IBM quantum hardware. The strongest results come from DCT representations paired with moderate-depth entangled QKS circuits.

A new arXiv paper introduces OCP-CT, a CT vision-language pretraining framework that aligns volumes and reports through organ-conditioned radiological pattern tokens. The work targets a key weakness of global scan-report contrastive learning: its tendency to blur heterogeneous organ-level evidence.

A new arXiv paper presents an adaptive digital twin framework for predicting brain tumor evolution and scheduling treatment. The approach combines a mechanistic reaction–diffusion model, 3D residual learning, online patient-specific updating, and model predictive control.

A new arXiv paper introduces Quantum Topological Data Encoding (QTDE), a framework for encoding geometric and topological structure into quantum states through topology-driven quantum evolution. Early experiments on clique-complex classification suggest that these quantum representations can outperform a baseline based on direct Laplacian comparisons.

A new arXiv paper presents a fully automated multimodal framework for assessing pancreatic ductal adenocarcinoma resectability. The system combines 3D contrast-enhanced CT with structured clinical variables to classify patients into NCCN resectability categories.