Improving the Diffusability of Motion Tokenizer
cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/eth-ait/aitviewer
Project page: https://githubhgh.github.io/dimot
Terminology
Sources
- LLaMA: Open and Efficient Foundation Language Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
- VideoPoet: A Large Language Model for Zero-Shot Video Generation
- Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations
- HumanPlus: Humanoid Shadowing and Imitation from Humans
- OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
- ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
- MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
- C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model
- Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
- Unified Number-Free Text-to-Motion Generation Via Flow Matching
- Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer
- Improving the Diffusability of Autoencoders
- Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
- Auto-Encoding Variational Bayes
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