M"obius: A Unified Motion-Language Model Bridging Understanding and Generation
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Project page: https://jiazhishu.github.io/mobius
Terminology
Sources
- Cosmos 3: Omnimodal World Models for Physical AI
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing
- Flexible Motion In-betweening with Diffusion Models
- UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
- Emerging Properties in Unified Multimodal Pretraining
- MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm
- LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Kimodo: Scaling Controllable Human Motion Generation
- Human Motion Diffusion Model
- Emu3: Next-Token Prediction is All You Need
- HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
- MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks
- Qwen3 Technical Report
- UniMuMo: Unified Text, Music and Motion Generation
- CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
- MotionGPT3: Human Motion as a Second Modality
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