Related papers: A MOSAIC of methods: Improving ortholog detection …
We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-refusal on benign boundary queries, and instruction following under verifiable constraints.…
Motivation Modern molecular sequence analysis increasingly relies on automated and robust software tools for interpretation, annotation, and biological insight. The Analysis of Orthologous Collections (AOC) application automates the…
We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked supervision. Our…
Codon usage bias has a crucial impact on the translation efficiency and co-translational folding of proteins, necessitating the algorithmic development of codon optimization/harmonization methods, particularly for heterologous recombinant…
Radiology reports contain rich clinical information that can be used to train imaging models without relying on costly manual annotation. However, existing approaches face critical limitations: rule-based methods struggle with linguistic…
The problem of representative selection amounts to sampling few informative exemplars from large datasets. This paper presents MOSAIC, a novel representative selection approach from high-dimensional data that may exhibit non-linear…
An oracle is a mechanism to decide whether the outputs of the program for the executed test cases are correct. For machine learning programs, such oracle is not available or too difficult to apply. Metamorphic testing is a testing approach…
Deep Learning models are easily disturbed by variations in the input images that were not observed during the training stage, resulting in unpredictable predictions. Detecting such Out-of-Distribution (OOD) images is particularly crucial in…
Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric misalignment between the merged encoder and static…
We introduce MOSAIC, a Python program for machine learning models. Our framework is developed with in mind accelerating machine learning studies through making implementing and testing arbitrary network architectures and data sets simpler,…
Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios…
Multi-subject personalized generation presents unique challenges in maintaining identity fidelity and semantic coherence when synthesizing images conditioned on multiple reference subjects. Existing methods often suffer from identity…
Capturing user intent across heterogeneous behavioral domains stands as a fundamental challenge in session-based recommender systems. Yet, existing multi-domain approaches frequently fail to isolate the distinct contribution of cross-domain…
Detecting out-of-distribution (OOD) samples is essential for neural networks operating in open-world settings, particularly in safety-critical applications. Existing methods have improved OOD detection by leveraging two main techniques:…
Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems. While a plethora of methods have been developed to…
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature. However, the field currently lacks a unified,…
Efficient and accurate multi-organ segmentation from abdominal CT volumes is a fundamental challenge in medical image analysis. Existing 3D segmentation approaches are computationally and memory intensive, often processing entire volumes…
Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learning models in the real world. Distance-based OOD detection…
In this paper, we propose a framework that incorporates experts diagnostics and insights into the analysis of Optical Coherence Tomography (OCT) using multi-modal learning. To demonstrate the effectiveness of this approach, we create a…
High-resolution Optical Coherence Tomography (OCT) images are crucial for ophthalmology studies but are limited by their relatively narrow field of view (FoV). Image mosaicking is a technique for aligning multiple overlapping images to…