Publikation
TextVision: A more efficient way to work with research
Melis Aslan; Maximilian Bosse; Daniel Christian Helmuth Ehlers; Marlon Hinz; Philipp Olschewski; Jannik Podszun; Elias Scharlach; Leon Selzer; Yukun Wu; Aliki Anagnostopoulou; Daniel Sonntag
In: - (Hrsg.). Joint Proceedings of the ACM IUI Workshops 2025. International Conference on Intelligent User Interfaces (IUI-2025), March 24-28, Cagliari, Italy, CEUR Proceedings, 2025.
Zusammenfassung
Large language models remain constrained by the limitations of current user interfaces and interaction paradigms, which hinder their ability to process complex, multimodal information beyond simple text input and output. Our proposed interface, TextVision, aims to address this limitation by enhancing how researchers interact with AI, providing a wide range of functionalities for analyzing, editing, creating new documents, and facilitating collaboration. TextVision advances state-of-the-art human-AI interaction through improved usability and novel interaction techniques, enhancing scientific research and development workflows. As a result, the user can access integrated tools, including a text editor, a PDF viewer, and an AI assistant in a chatbot format. The AI assistant can provide answers based on user input and is context-aware. This output can be enhanced using the built-in prompt designing tool to create efficient, AI-optimized prompts. Users can also select between the latest proprietary LLMs and fine-tuned open-source models tailored for specific tasks.