Compact Motion Embeddings for Feed-forward Unified Human Animation
cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/madebyollin/taesd
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis
- Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
- LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
- In Defense of the Triplet Loss for Person Re-Identification
- RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
- RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation
- C-RADIOv4 (Tech Report)
- DINOv3
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
- SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
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