Progressively Learning Heterogeneous Skills in a Unified Latent Space
cs.CV, cs.AI, cs.RO
Submitted: 2026-08-24
Updated: 2026-08-24
Code: https://github.com/NVLabs/ProtoMotions
Terminology
Sources
- Understanding disentangling in $\beta$-VAE
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- Goal-Conditioned Reinforcement Learning: Problems and Solutions
- Universal Humanoid Motion Representations for Physics-Based Control
- From Universal Humanoid Control to Automatic Physically Valid Character Creation
- Neural probabilistic motor primitives for humanoid control
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
- Parameter Space Noise for Exploration
- Proximal Policy Optimization Algorithms
- OpenAI GPT-5 System Card
- CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
- Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models