Related papers: SAGE: Agentic Framework for Interpretable and Clin…
Large language models are unable to continuously adapt and learn from new data during reasoning at inference time. To address this limitation, we propose that complex reasoning tasks be decomposed into atomic subtasks and introduce SAGE, a…
Hypothesis generation in biomedical research has traditionally centered on uncovering hidden relationships within vast scientific literature, often using methods like Literature-Based Discovery (LBD). Despite progress, current approaches…
We present Semantic-Aware Guided Exploration, SAGE, a system for open-vocabulary exploration in unknown 3D indoor environments that preserves coverage-oriented behavior while allowing semantic cues to reprioritize frontier selection.…
Large language models (LLMs) have proven to work well in question-answering scenarios, but real-world applications often require access to tools for live information or actuation. For this, LLMs can be extended with tools, which are often…
We envision "AI scientists" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with experimental platforms. Rather than taking…
Enumerated threat agent lists have long driven biodefense priorities. The global SARS-CoV-2 pandemic demonstrated the limitations of searching for known threat agents as compared to a more agnostic approach. Recent technological advances…
A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast…
Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic…
EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier to clinical trust. We apply TopK Sparse Autoencoders (SAEs) across three architecturally…
Computational biomarkers (CBs) are histopathology-derived patterns extracted from hematoxylin-eosin (H&E) whole-slide images (WSIs) using artificial intelligence (AI) to predict therapeutic response or prognosis. Recently, slide-level…
Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced analytical decisions, e.g., about which variables,…
Interpretability is a pressing issue for decision systems. Many post hoc methods have been proposed to explain the predictions of a single machine learning model. However, business processes and decision systems are rarely centered around a…
Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs) offer a promising path to enhance healthcare predictions by…
We explore the potential for combining generative AI with grammar-based visualizations for biomedical data discovery. In our prototype, we use a multi-agent system to generate visualization specifications and apply filters. These…
Advancements in generative Artificial Intelligence (AI) hold great promise for automating radiology workflows, yet challenges in interpretability and reliability hinder clinical adoption. This paper presents an automated radiology report…
Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose SAGE, a…
Recent advances in computational pathology have led to the emergence of numerous foundation models. These models typically rely on general-purpose encoders with multi-instance learning for whole slide image (WSI) classification or apply…
Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and…
In today's data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in making effective decisions. With the rapid advancement of…
Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…