Related papers: MOSAIC: A Multilingual, Taxonomy-Agnostic, and Com…

Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensive, inconsistent, and difficult to scale. Existing approaches based on large language models…

Reinforcement learning (RL), large language models (LLMs), and vision-language models (VLMs) have been widely studied in isolation. However, existing infrastructure lacks the ability to deploy agents from different decision-making paradigms…

We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require algorithms that are rigorous, interconnected with deep domain…

Reliably ensuring Large Language Models (LLMs) follow complex instructions is a critical challenge, as existing benchmarks often fail to reflect real-world use or isolate compliance from task success. We introduce MOSAIC (MOdular Synthetic…

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…

We present a next-generation neural network architecture, MOSAIC, for efficient and accurate semantic image segmentation on mobile devices. MOSAIC is designed using commonly supported neural operations by diverse mobile hardware platforms…

A holistic understanding of object properties across diverse sensory modalities (e.g., visual, audio, and haptic) is essential for tasks ranging from object categorization to complex manipulation. Drawing inspiration from cognitive science…

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

Generating radiology reports automatically reduces the workload of radiologists and helps the diagnoses of specific diseases. Many existing methods take this task as modality transfer process. However, since the key information related to…

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.…

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…

Medical audio data is difficult to collect due to privacy regulations and high annotation costs arising from domain expertise. Thus, existing benchmarks tend to underrepresent complex medical audio scenarios. To address this challenge, we…

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,…

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and…

Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary across users, regions,…

Recent advances in histopathology vision-language foundation models (VLFMs) have shown promise in addressing data scarcity for whole slide image (WSI) classification via zero-shot adaptation. However, these methods remain outperformed by…

Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tracking from electronic health records (EHRs). Existing systems typically rely on manually…

Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a…

Automatic radiology report generation is a promising application of multimodal deep learning, aiming to reduce reporting workload and improve consistency. However, current state-of-the-art (SOTA) systems - such as Multimodal AI for…

Large language models (LLMs) have shown considerable promise in clinical natural language processing, yet few domain-specific datasets exist to rigorously evaluate their performance on radiology tasks. In this work, we introduce an…