Action Transfer Across Character Body Plans in Latent-Action World Models: An Empirical Study of Animated Characters
cs.CV, cs.GR, cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- World Models
- Genie: Generative Interactive Environments
- Learning to Act without Actions
- AdaWorld: Learning Adaptable World Models with Latent Actions
- RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions
- SCAR: Self-Supervised Continuous Action Representation Learning
- CLAW: Continuous Latent Action World Models via Adversarial Regularization
- DiLA: Disentangled Latent Action World Models
- Olaf-World: Orienting Latent Actions for Video World Modeling
- Learning Latent Action World Models In The Wild
- 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface
- Disentangled Sequential Autoencoder
- Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision
- Transfer Learning for Pose Estimation of Illustrated Characters
- APES: Articulated Part Extraction from Sprite Sheets
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs