University of Florida Data Studio 🐊

The UF Data Studio is home for research projects for all parts of the Data Pipeline. We are passionate about developing new ways humans can interact with their data and understanding the fundamental research issues all along the data pipeline.

Avatar image
Latest Updates
Top right corner of Figure 3 from the WMT26 findings paper, with an alligator marking the gators point, the highest BLEU and COMET scores for Manipuri (Bengali script) to English.

Gators at WMT26: Retrieval-Augmented Many-Shot Translation for Low-Resource Northeast Indian Languages

Oct 22, 2026
Team Gators built a WMT26 Indic translation system from BM25 retrieval and many-shot prompting with Gemini 2.5 Flash. It uses no fine-tuning, covers 22 language and direction pairs, and leads on ChrF++ for 10 of the 20 pairs with published per-system scores.
Future Retrieval

Future Retrieval

Aug 7, 2026
What Does the Future Talk About?
Figure 1 from Zhang et al. (ACL 2026), showing the LoopTool closed-loop pipeline for iterative tool-use enhancement.

LoopTool — When Tool-Use Training Needs a Closed Loop

Aug 1, 2026
A blogpost on an ACL 2026 paper that couples GRPO training with greedy probing, judge-guided label repair, and error-driven data expansion for robust LLM function calling.
Highrise buildings standing on the left of streetlights and streetlamps with the overhanging roof and tall glass facade of the Colorado Convention Center looming to the right.

RAN Notation - Introducing Objectivity to Descriptions of Resource Scarcity in NLP

Jul 31, 2026
We discuss a recent breakthrough in language documentation. Researchers introduce a new formalism to concisely communicate the number of speakers and corpus sizes of languages.

Veridicality

Jul 31, 2026
Forecasting Winners and Losers from User Predictions on Twitter
High rise buildings standing on the left of streetlights and streetlamps with the overhanging roof and tall glass facade of the Colorado Convention Center looming to the right.

The OpenMantra Dataset for Multimodal Manga Translation

Jul 31, 2026
OpenMantra is a dataset from the same lab behind Manga109, published in 2021. In this post, we contrast OpenMantra with the much more well known Manga109, and we discuss how the UF Data Studio may use it in the future.
View all posts →

Proudly Funded By

© Copyright 2026 by UF Data Studio. Built with ♥ by ceg.me. [trailers]