Introduces a standardized human evaluation protocol for speech-driven gesture generation on BEAT2 and benchmarks six models, revealing saturated motion realism and unreliable prior alignment scores.
A V-Flow: Transforming text to audio-visual human-like interactions.arXiv preprint arXiv:2502.13133
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ELEVATE is a framework and prototype for deploying LLM-powered 3D avatar tutors locally on consumer hardware with a three-stratum design separating interaction, execution, and governance layers.
citing papers explorer
-
Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark
Introduces a standardized human evaluation protocol for speech-driven gesture generation on BEAT2 and benchmarks six models, revealing saturated motion realism and unreliable prior alignment scores.
-
ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education
ELEVATE is a framework and prototype for deploying LLM-powered 3D avatar tutors locally on consumer hardware with a three-stratum design separating interaction, execution, and governance layers.