As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning ...
Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated support examples. Existing prototype-based methods typically construct compa...
Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what intern...
Marine bioactive materials are obtained from diverse organisms, which include algae, sponges, corals, and mollusks. These materials possess unique chemical structures and evolutionary traits that prov...
Microplastics (MPs) contaminate marine environments from surface waters to deep sediments. Approximately half of global plastic production consists of low-density polymers that should float in seawate...
Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffec...
Photosynthetic microorganisms are responsible for primary production at the base of the marine food web and influence global biogeochemistry. Their growth is balanced by mortality processes, including...
The Greenland shark (Somniosus microcephalus), with a lifespan estimated around 300 years, represents a unique model for studying vertebrate longevity. Here, we characterize its cardiac aging profile ...
We consider the problem of sampling from a posterior distribution arising in Bayesian inverse problems in science, engineering, and imaging. Our method belongs to the family of independence Metropolis...
Cancer subtyping plays a crucial role in informing prognosis and guiding personalized treatment strategies. However, conventional subtyping approaches often rely on static, biopsy-derived scores that ...
The two-point correlation function (2PCF) is a cornerstone of precision cosmology, yet its estimation from imaging surveys is vulnerable to contamination and incompleteness arising from imperfect targ...
Suspension feeding, in which organisms filter particles from the water for nutrition, is a widespread and ecologically critical feeding strategy in aquatic ecosystems. And yet, the principles governin...
Microplastic pollution, stemming from plastic degradation or direct release, presents a persistent threat to marine environments. While global concern grows, data from the Indian Ocean, especially on ...
Background: Medical Digital Twins (MDTs) are computational representations of individual patients that integrate clinical, genomic, and physiological data to support diagnosis, treatment planning, and...
Understanding the interplay between high-dimensional data from different views is essential in biomedical research, particularly in fields such as genomics, neuroimaging and biobank-scale studies invo...
Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by atypical brain connectivity. One of the crucial steps in addressing ASD is its early detection. This study introduces ...
Augmented reality (AR) devices with head mounted displays (HMDs) facilitate the direct superimposition of 3D preoperative imaging data onto the patient during surgery. To use an HMD-AR device as a sta...
Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model by transmitting loca...
We introduce a novel conditional stochastic interpolant framework for generative modeling of three-dimensional shapes. The method builds on a recent LDDMM-based registration approach to learn the cond...
The direct imaging of potentially habitable exoplanets is one prime science case for high-contrast imaging instruments on extremely large telescopes. Most such exoplanets orbit close to their host sta...
