16 papers this week in AI for science & health12 active threadsbusiest: Agent Security & Attacks

AI for science & health research

Evaluation & benchmarks

AI agents fail end-to-end physics research due to shallow reasoning and missing intuition

The authors introduce FrontierPhysics, a benchmark with 56 research tasks created by 42 physicists based on their own work. They evaluated 22 models across 26 configurations and found that no configuration passed more than 46 out of 168 rollouts. Manual review revealed that the main weaknesses are insufficiently rigorous reasoning and limited expert intuition, not gaps in physics knowledge.

3 days ago
Evaluation & benchmarks

Flexible classical models match neural networks for event prediction, but not on ICU data

The authors systematically compared classical Hawkes processes and neural temporal point processes (TPPs) for modeling event sequences, using flexible parametrizations. They found that the previously reported gap between the two families largely disappears when Hawkes processes are equipped with learnable, spline-based baselines and kernels. However, on complex medical data from MIMIC-IV, neural TPPs still outperform classical models, particularly in predicting event types.

3 days ago
Evaluation & benchmarks

Visual AI models often can't count animals or tell individuals apart

Researchers from Rensselaer Polytechnic Institute created Bio-VQA, the largest biological visual question-answering benchmark, containing 1.86 million questions over 217,000 images. They evaluated 18 open-weight vision-language models and found that general visual capabilities do not transfer to biological imagery: the best model counts animals exactly on 41.7% of images with two to ten individuals, and 17 of the 18 models fall below chance when asked whether two photographs show the same individual.

4 days ago
Vision

AI that identifies radiological findings first can diagnose unseen diseases

The authors introduce Diagnosis by Composition (DbC), a framework that first learns to recognize radiological findings from images by aligning features with text embeddings, then combines these findings to diagnose diseases per published guidelines. On multi-phase liver CT, DbC significantly outperformed all comparators in detecting and localizing diseases not seen during training, including rare diseases from external institutions.

4 days ago
AI for science & health

AI forecasting model adapts to sensor changes, guarantees uncertainty at new locations

The authors propose OmniST, a topology-invariant spatiotemporal forecaster that does not depend on the number of sensor nodes. Composed with inductive split-conformal calibration, it provides distribution-free prediction intervals with coverage guarantees at unseen locations. On real air quality, weather, and traffic data, it achieves competitive accuracy and degrades minimally under sensor dropout.

4 days ago