Retrieval from motion datasets combined with LLM task parsing and reward-guided noise initialization enables training-free diffusion optimization to satisfy severe spatiotemporal constraints in human motion generation.
Vimorag: Video-based retrieval-augmented 3d motion generation for motion language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
SentiAvatar generates expressive interactive 3D avatars in real time by combining a 37-hour mocap dialogue dataset with a pre-trained motion foundation model and an audio-aware plan-then-infill architecture that separates semantic planning from prosody-driven frame interpolation.
citing papers explorer
-
Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization
Retrieval from motion datasets combined with LLM task parsing and reward-guided noise initialization enables training-free diffusion optimization to satisfy severe spatiotemporal constraints in human motion generation.
-
SentiAvatar: Towards Expressive and Interactive Digital Humans
SentiAvatar generates expressive interactive 3D avatars in real time by combining a 37-hour mocap dialogue dataset with a pre-trained motion foundation model and an audio-aware plan-then-infill architecture that separates semantic planning from prosody-driven frame interpolation.