UNIPO is the first unified interactive visualization tool exposing token-level training dynamics of RL fine-tuning algorithms for LLMs through high-level overviews, step inspectors, and side-by-side comparisons.
Ge, Yiren Ding, Fumeng Yang, Lane Harrison, and Matthew Kay
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.HC 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Interviews with practitioners and educators yield a systematic account of annotation design considerations, trade-offs, and contextual judgments in visualization practice.
The paper introduces KI-Adventskalender, an online daily challenge series for data and AI literacy, and reports higher participation in 2025 with persistent early attrition and stabilization after day 12.
citing papers explorer
-
UNIPO: Unified Interactive Visual Explanation for RL Fine-Tuning Policy Optimization
UNIPO is the first unified interactive visualization tool exposing token-level training dynamics of RL fine-tuning algorithms for LLMs through high-level overviews, step inspectors, and side-by-side comparisons.
-
Designing Annotations in Visualization: Considerations from Visualization Practitioners and Educators
Interviews with practitioners and educators yield a systematic account of annotation design considerations, trade-offs, and contextual judgments in visualization practice.
-
KI-Adventskalender: An Informal Learning Intervention for Data & AI Literacy
The paper introduces KI-Adventskalender, an online daily challenge series for data and AI literacy, and reports higher participation in 2025 with persistent early attrition and stabilization after day 12.