motion-generation

Tag

Cards List
#motion-generation

Generative Learning as a Tool to Improve Perception of Emotional Body Motion Expressions

arXiv cs.LG · 2026-06-30 Cached

This paper investigates using a Transformer-based generative model to learn emotional body motions from motion-capture data of Japanese actors, generating motions conditioned on discrete emotion labels. Evaluations show the generated motions improve emotion recognition when used for data augmentation and enable smooth transitions between emotion intensities.

0 favorites 0 likes
#motion-generation

PhysiFormer: Learning to Simulate Mechanics in World Space

Hugging Face Daily Papers · 2026-06-25 Cached

PhysiFormer uses coordinate-space diffusion to generate physically-plausible 3D object motions without explicit inductive biases, enabling efficient multi-object reasoning and generalization to complex materials and geometries.

0 favorites 0 likes
#motion-generation

PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation

arXiv cs.AI · 2026-06-20 Cached

This paper identifies an embodiment gap in humanoid co-speech motion generation caused by human-centric pipelines, and proposes PhysDrift, an embodiment-aware framework that directly predicts executable humanoid joint trajectories from speech, improving speech-motion alignment and physical plausibility.

0 favorites 0 likes
#motion-generation

MotionVLA: Vision-Language-Action Model for Humanoid Motion

Hugging Face Daily Papers · 2026-06-13 Cached

Proposes MotionVLA, a vision-language-action model for humanoid motion generation using a dual-stream frequency tokenizer that separately encodes pose and physical dynamics, achieving better diversity and consistency.

0 favorites 0 likes
#motion-generation

VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

Hugging Face Daily Papers · 2026-06-11 Cached

VideoMDM trains 3D human motion priors from 2D poses using a diffusion framework with 2D reprojection loss and 3D motion regularizers, achieving near-3D supervised performance without requiring 3D ground truth.

0 favorites 0 likes
#motion-generation

GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors

Hugging Face Daily Papers · 2026-06-03 Cached

GRAIL generates diverse humanoid manipulation and locomotion data using 3D assets and video foundation models, enabling effective sim-to-real transfer for humanoid robot control with high real-world success rates.

0 favorites 0 likes
← Back to home

Submit Feedback