ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
Videogen-eval: Agent-based system for video generation evaluation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
fields
cs.CV 4verdicts
UNVERDICTED 4roles
background 4polarities
background 4representative citing papers
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
LPM 1.0: Video-based Character Performance Model
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.