Scientific Discovery & Drug Design

Anomaly detection in EHR data can pinpoint potentially erroneous clinical decisions with surprisingly low false alarm rates, suggesting a practical pathway to improve patient safety.

LLMs can now impute missing healthcare data well enough to improve causal treatment effect estimation from real-world EHRs, even with 80% missingness.

Stabilizing nuclear fusion plasma with imitation learning is possible even with limited macroscopic observations, offering a path to practical control strategies.

Don't let your materials science dataset become obsolete: a diversity-aware construction framework can boost performance on both targeted and *untargeted* properties by up to 40%.

Forget expensive on-site inspections: this multimodal model uses assessor text and GIS data to accurately predict building energy performance, enabling scalable retrofit planning.

Discovering spatial regions and their temporal signatures in massive time series data just got much faster and easier, thanks to a new method that scales log-linearly with the number of time series.

Nanometer-accurate, full-chip CMP modeling is now possible with a fast, FCN-based approach that leapfrogs traditional, resource-intensive methods.

Forget trying to shoehorn hypergraphs into pairwise representations – this diffusion model directly generates them from incidence matrices, unlocking more realistic and complex structures.

Inverting time-domain marine electromagnetic data, a traditionally computationally intensive task, can now be done 21,000x faster with a deep learning model that also outperforms traditional optimization methods.

Conformal prediction for graph time series doesn't have to break down: by conditioning on low-frequency trends, you can restore exchangeability and get valid uncertainty estimates.

Causal gene regulatory network inference methods only dominate when data is pristine; common single-cell data pathologies like dropout and latent confounders selectively negate their advantages.

Neural networks can now discover previously unknown behavior in hard PDE problems, revealing that Strichartz extremizers for the critical Airy equation are not attained but approached by mKdV breathers.

Reservoir Computing offers a surprisingly effective way to build Koopman dictionaries for nonlinear system identification, sidestepping the usual dictionary selection and ill-conditioning problems.

Feature importance in machine learning models can be surprisingly unreliable: even when models predict accurately, the features they deem important can vary wildly, especially with small datasets.

Unstable BO leaderboard rankings? They're likely due to ignoring the budget ratio (B/|A|) and prior rank correlation, which this paper elegantly captures with the Portable Regime Score (PRS) to predict performance reversals.

Neural operators can stably and accurately correct the structured truncation errors of classical numerical solvers for dispersive PDEs, even with rough data.

GNN uncertainty just got a whole lot easier: QpiGNN delivers better coverage and tighter intervals without the quantile gymnastics.

Existing causal discovery methods can be dangerously wrong when data is missing, but PAIR-CI slashes false positives by directly accounting for imputation errors, leading to more accurate causal graphs.

Physics-informed neural operators can now learn continually without forgetting, thanks to a simple replay strategy that preserves past knowledge while rapidly adapting to new out-of-distribution data.

A hybrid AI model can boost corn yield predictions by up to 7.2%, offering a promising path to accelerate climate-adapted crop development.

AI can now discover and suggest genuinely novel mathematical inequalities, hinting at its potential for breakthroughs beyond traditional theorem proving.

By embedding whole-slide images in a hybrid hyperbolic-Euclidean space, BatMIL unlocks superior classification performance compared to traditional Euclidean-only methods, revealing the importance of geometric awareness in capturing complex tissue organization.

Coordinating LLM agents with evolving knowledge graphs, rather than just text, unlocks superior scientific ideation, beating state-of-the-art systems on multiple benchmarks.

Frontier LLMs are leaving 70% of relevant pharmaceutical assets undiscovered, a gap that can be largely closed by swapping generic web search for a curated index.

Forget expert intuition – language trends in patent filings can foresee technological breakthroughs years before they happen.

Optimizing wildfire suppression via integer programming and machine learning can significantly reduce burned areas and improve resource allocation, offering a data-driven approach to a critical real-world problem.

LLMs ace MRI multiple-choice tests, but can't actually recall basic facts about GE scanners, revealing a dangerous gap between perceived and actual competence.

Patents overselling their innovation actually face a *penalty* in evaluation, decreasing their chances of being granted, transferred, or successfully appealed.

Vol-Mark offers a way to protect sensitive 3D medical data from tampering and unauthorized copying with a reversible watermarking technique that maintains diagnostic accuracy.

Counterintuitively, moderately similar reference images are the key to unlocking accurate VLM-based anomaly localization in medical imaging.

Even with limited data, a simple combination of pre-trained CNN features and nearest-centroid classification can achieve surprisingly strong results in monkeypox skin disease classification.

For more reliable animal identification, force your model to reconstruct masked skin patterns, and it will learn embeddings that better capture individual differences.

Generate CT-like images from ultrasound with a transformer-augmented network, potentially reducing the need for harmful radiation exposure.

Forget PEFT and KD, reprogramming distillation offers a surprisingly effective and robust way to adapt large medical foundation models to diverse downstream tasks.

Condensin's loop extrusion mechanism relies on catch bonds, meaning that, counterintuitively, applying a small amount of force actually *increases* the lifetime of a key intermediate state.

Forget digital watermarks – now you can physically fingerprint solutions with electrochemically-generated polymer patterns, opening doors to low-cost, physically-encrypted personal information.

Automating diabatization with neural networks unlocks accurate simulation of complex non-adiabatic molecular dynamics, revealing unexpected fragmentation pathways.

Unlock highly accurate and efficient electronic structure calculations with "angular gausslets," a new basis that diagonalizes the electron-electron interaction, enabling precise DMRG computations for complex atoms.

Brain tumor segmentation gets a lightweight boost: DALight-3D achieves comparable accuracy to larger U-Nets with significantly fewer parameters.

Random masking in self-supervised learning can destroy crucial diagnostic features in medical images; instead, try inverting chaos.

Spatial transcriptomics predictions get a boost from HEXST, a Transformer that respects the hexagonal geometry of spot arrays and recovers gene-specific spatial heterogeneity.

Turns out, deep learning models trained to predict breast density from ultrasound images generalize surprisingly well to external datasets, but still struggle with heterogeneously dense breasts.

Automating materials science database construction is now feasible: a multi-agent system extracts structured data from scientific literature with high speed and accuracy.

Clinicians trust AI recommendations nearly 3x more when those recommendations are broken down into verifiable facts linked to source guidelines, blowing traditional explainability out of the water.

Despite fears of rampant misinformation, Bluesky discussions of retracted science papers overwhelmingly demonstrate "good practice" like acknowledging retractions, suggesting social media can support research integrity.

Knowing how the public reacts to AI breakthroughs can help predict the *next* breakthrough, but only if you model the relationship as a directional coupling between innovation and response.

CBAM could reshape Europe's electricity market, giving low-carbon countries a competitive edge while burdening high-carbon economies.

Predicting ICU admission risk from patient data improves from AUC 0.642 to 0.942 as more clinical events are observed, highlighting the value of continuous, dynamically aware predictive monitoring.

Forget iterative approximations – this work delivers globally optimal solutions for unbalanced optimal transport between Gaussians via a clever reduction to finite-dimensional optimization.

Simulating complex fluid dynamics with moving boundaries just got 20x faster thanks to a new GPU-optimized immersed boundary method.