相关论文: SciFig: Towards Automating Scientific Figure Gener…
Creating presentation materials requires complex multimodal reasoning skills to summarize key concepts and arrange them in a logical and visually pleasing manner. Can machines learn to emulate this laborious process? We present a novel task…
Automatic survey generation has emerged as a key task in scientific document processing. While large language models (LLMs) have shown promise in generating survey texts, the lack of standardized evaluation datasets critically hampers…
The accelerating growth of scientific publications has intensified the need for scalable, trustworthy systems to synthesize knowledge across diverse literature. While recent retrieval-augmented generation (RAG) methods have improved access…
Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving…
We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks. These tasks span five core scientific literature…
Keeping pace with the rapid growth of academia literature presents a significant challenge for researchers, funding bodies, and academic societies. To address the time-consuming manual effort required for scholarly discovery, we present a…
The rapid expansion of scholarly literature presents significant challenges in synthesizing comprehensive, high-quality academic surveys. Recent advancements in agentic systems offer considerable promise for automating tasks that…
Figures visually represent an essential piece of information and provide an effective means to communicate scientific facts. Recently there have been many efforts toward extracting data directly from figures, specifically from tables,…
In an era where visual content generation is increasingly driven by machine learning, the integration of human feedback into generative models presents significant opportunities for enhancing user experience and output quality. This study…
Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to…
Definitions are the foundation for any scientific work, but with a significant increase in publication numbers, gathering definitions relevant to any keyword has become challenging. We therefore introduce SciDef, an LLM-based pipeline for…
This paper examines the potential for generative artificial intelligence (GenAI) to assist with internal review processes for research quality evaluations in UK higher education and particularly in preparation for the Research Excellence…
Academic poster generation is a crucial yet challenging task in scientific communication, requiring the compression of long-context interleaved documents into a single, visually coherent page. To address this challenge, we introduce the…
Artificial Intelligence (AI) has been increasingly applied to creative domains, leading to the development of systems that collaborate with humans in design processes. In Graphic Design, integrating computational systems into co-creative…
Intelligent tutoring systems have long enabled automated immediate feedback on student work when it is presented in a tightly structured format and when problems are very constrained, but reliably assessing free-form mathematical reasoning…
AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond…
Automatically extracting key information from scientific documents has the potential to help scientists work more efficiently and accelerate the pace of scientific progress. Prior work has considered extracting document-level entity…
Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text…
Scientific writing involves retrieving, summarizing, and citing relevant papers, which can be time-consuming processes in large and rapidly evolving fields. By making these processes inter-operable, natural language processing (NLP)…
Academic posters are vital for scholarly communication, yet their manual creation is time-consuming. However, automated academic poster generation faces significant challenges in preserving intricate scientific details and achieving…