MotionMERGE proposes a multi-granular LLM framework for fine-grained text-driven human motion editing, reasoning, generation, and explanation, supported by the new MotionFineEdit dataset with spatio-temporal annotations.
Exploring the limits of transfer learning with a unified text-to-text transformer,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Fisher information geometry supplies parameterization-invariant metrics for MoE specialization dynamics and early failure prediction with strong empirical correlations.
citing papers explorer
-
MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation
MotionMERGE proposes a multi-granular LLM framework for fine-grained text-driven human motion editing, reasoning, generation, and explanation, supported by the new MotionFineEdit dataset with spatio-temporal annotations.
-
Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection
Fisher information geometry supplies parameterization-invariant metrics for MoE specialization dynamics and early failure prediction with strong empirical correlations.