Aggregating many LLM-synthesized weak verifiers via weak learning from sparse labels yields stronger verifiers that improve F1 by up to 7X over direct LLM judges on 3D room and 2D poster tasks and boost generation quality by 66.2%.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DataSway supports creation of semantically aligned animations for metaphoric data visualizations by generating clips via VLMs and coordinating timelines based on entity order, attributes, layout, or randomness.
citing papers explorer
-
Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation
Aggregating many LLM-synthesized weak verifiers via weak learning from sparse labels yields stronger verifiers that improve F1 by up to 7X over direct LLM judges on 3D room and 2D poster tasks and boost generation quality by 66.2%.
-
DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination
DataSway supports creation of semantically aligned animations for metaphoric data visualizations by generating clips via VLMs and coordinating timelines based on entity order, attributes, layout, or randomness.