Related papers: VERITAS: Verifiable Epistemic Reasoning for Image-…
Medical Visual Question Answering (MedVQA), which offers language responses to image-based medical inquiries, represents a challenging task and significant advancement in healthcare. It assists medical experts to swiftly interpret medical…
AI tools in pathology have improved screening throughput, standardized quantification, and revealed prognostic patterns that inform treatment. However, adoption remains limited because most systems still lack the human-readable reasoning…
The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI…
Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in…
Automated fact-checking is a crucial task that supports a responsible information ecosystem. While recent research has progressed from text-only to multimodal fact-checking, a prevailing assumption is that incorporating visual evidence…
Data scarcity and unreliable self-reporting -- such as concealment or exaggeration -- pose fundamental challenges to psychiatric intake and assessment. We propose a multi-agent synthesis framework that explicitly models patient deception to…
Polycystic Ovary Syndrome (PCOS) constitutes a significant public health issue affecting 10% of reproductive-aged women, highlighting the critical importance of developing effective diagnostic tools. Previous machine learning and deep…
Large language models (LLMs) become increasingly integrated into data science workflows for automated system design. However, these LLM-driven data science systems rely solely on the internal reasoning of LLMs, lacking guidance from…
Breast ultrasound diagnosis typically proceeds from global lesion localization to local sign assessment and then evidence integration to assign a BI-RADS category and determine benignity or malignancy. Many existing methods rely on…
We study the extension of relational multiagent systems (RMASs), where agents manipulate full-fledged relational databases, with data types and facets equipped with domain-specific, rigid relations (such as total orders). Specifically, we…
Multimodal large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning that requires deep searching and integrating visual evidence with external…
Multimodal/vision language models (VLMs) are increasingly being deployed in healthcare settings worldwide, necessitating robust benchmarks to ensure their safety, efficacy, and fairness. Multiple-choice question and answer (QA) datasets…
Whole slide images (WSIs) are vital in digital pathology, enabling gigapixel tissue analysis across various pathological tasks. While recent advancements in multi-modal large language models (MLLMs) allow multi-task WSI analysis through…
Legal Judgment Prediction (LJP) predicts applicable law articles, charges, and penalty terms from case facts. Beyond accuracy, LJP calls for intrinsically interpretable and legally grounded reasoning that can reconcile statutory rules with…
The scientific claim verification task requires an NLP system to label scientific documents which Support or Refute an input claim, and to select evidentiary sentences (or rationales) justifying each predicted label. In this work, we…
Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…
Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-structured tables. However, while methods like…
Healthcare and medicine are multimodal disciplines that deal with multimodal data for reasoning and diagnosing multiple diseases. Although some multimodal reasoning models have emerged for reasoning complex tasks in scientific domains,…
Large language models have achieved strong performance on medical reasoning benchmarks, yet their deployment in clinical settings demands rigorous verification to ensure factual accuracy. While reward models offer a scalable approach for…