Related papers: A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline…
The challenge of navigation in environments with dynamic objects continues to be a central issue in the study of autonomous agents. While predictive methods hold promise, their reliance on precise state information makes them less practical…
Interactive visual analysis interfaces are critical in nearly every data task. However, creating new interfaces is deeply challenging, as it requires the developer to understand the queries needed to express the desired analysis task,…
Understanding and extracting structured insights from unstructured documents remains a foundational challenge in industrial NLP. While Large Language Models (LLMs) enable zero-shot extraction, traditional pipelines often fail to handle…
This paper introduces Agentics, a functional agentic AI framework for building LLM-based structured data workflow pipelines. Designed for both research and practical applications, Agentics offers a new data-centric paradigm in which agents…
Agentic systems have recently emerged as a promising tool to automate literature-based ideation. However, current systems often remain black-box, with limited transparency or control for researchers. Our work introduces TrustResearcher, a…
Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code…
Creating data stories from raw data is challenging due to humans' limited attention spans and the need for specialized skills. Recent advancements in large language models (LLMs) offer great opportunities to develop systems with autonomous…
Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework…
Effective data analysis ideally requires the analyst to have high expertise as well as high knowledge of the data. Even with such familiarity, manually pursuing all potential hypotheses and exploring all possible views is impractical. We…
Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive pipelines. We…
Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, modern methods (e.g., VIP and R3M) still face significant hurdles, notably the…
Artificial agents are increasingly integrated into data analysis workflows, carrying out tasks that were primarily done by humans. Our research explores how the introduction of automation re-calibrates the dynamic between humans and…
In recent years, a wide variety of automated machine learning (AutoML) methods have been proposed to search and generate end-to-end learning pipelines. While these techniques facilitate the creation of models for real-world applications,…
Diagnosing a whole-slide image is an interactive, multi-stage process of changing magnification and moving between fields. Although recent pathology foundation models demonstrated superior performances, practical agentic systems that decide…
We present a visualization infrastructure that maps data elements to agents, which have behaviors parameterized by those elements. Dynamic visualizations emerge as the agents change position, alter appearance and respond to one other.…
Building Large Language Model agents that expand their capabilities by interacting with external tools represents a new frontier in AI research and applications. In this paper, we introduce InfoAgent, a deep research agent powered by an…
As machine learning (ML) systems become increasingly widespread, it is necessary to audit these systems for biases prior to their deployment. Recent research has developed algorithms for effectively identifying intersectional bias in the…
With the rise of the open data movement a lot of statistical data has been made publicly available by governments, statistical offices and other organizations. First efforts to visualize are made by the data providers themselves. Data…
In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their…
In the last ten years, various automated machine learning (AutoM ) systems have been proposed to build end-to-end machine learning (ML) pipelines with minimal human interaction. Even though such automatically synthesized ML pipelines are…