AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
cs.CV, cs.AI
Submitted: 2026-05-28
Updated: 2026-10-29
Code: https://github.com/Breakthrough/PySceneDetect
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
- RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation
- YOLOv11: An Overview of the Key Architectural Enhancements
- VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension
- Finite Scalar Quantization: VQ-VAE Made Simple
- BAMM: Bidirectional Autoregressive Motion Model
- Kimodo: Scaling Controllable Human Motion Generation
- LLaMA: Open and Efficient Foundation Language Models
- Scaling Large Motion Models with Million-Level Human Motions
- HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
- OmniControl: Control Any Joint at Any Time for Human Motion Generation
- LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
- T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
- OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
- Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset
- Motion Anything: Any to Motion Generation
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
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