arXiv Computer Vision
SeMoCo: A Semantic-First Motion Codec for Motion Language Modeling
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 31
MUGEN: A Unified Framework for Efficient Motion Understanding and Generation
arXiv:2607. 27581v1 Announce Type: new Abstract: Grounding human motion in language, and language in motion, is a central step toward physical AI systems that can understand, generate, and communicate human behavior.
Hugging Face Trending Papers
Jun 28
Zero-Gated Language-conditioned Human Motion Prediction
Pose histories provide the core kinematic evidence for 3D human motion prediction, but they lack explicit high-level semantic guidance. This paper introduces ZGL, a lightweight language-conditioned predictor that uses captions of the observed motion as a semantic prior while preserving a strong motion backbone as the main source of dynamics.
arXiv Computer Vision
2d ago
PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition
arXiv:2603.08590v4 Announce Type: replace Abstract: Text-to-motion generation has advanced with larger corpora and stronger generators, yet many models still rely on holistic frame- or clip-level lat...
arXiv AI
Jun 8
MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models
arXiv:2606. 06853v1 Announce Type: cross Abstract: The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding.
arXiv AI
Jun 2
Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
arXiv:2606. 01014v1 Announce Type: cross Abstract: We address text-based 3D human motion editing, where the goal is to preserve the style and structure of a source motion while applying edits described in natural language.
Hugging Face Trending Papers
Aug 10
UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation
Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity.