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.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
GFlowState introduces interactive visualizations such as trajectory node-link diagrams and transition heatmaps to make GFlowNet training dynamics observable for debugging and quality assessment.
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.
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.
-
Making Abstraction Concrete: A Design Space and Interaction Model of Abstraction in Interactive Systems
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
-
GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward
GFlowState introduces interactive visualizations such as trajectory node-link diagrams and transition heatmaps to make GFlowNet training dynamics observable for debugging and quality assessment.
-
HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.