A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting
cs.GR, cs.AI, cs.CV
Submitted: 2026-04-15
Updated: 2026-09-10
Terminology
Sources
- Qwen3-VL Technical Report
- Multi-Embodiment Robotic Retargeting via Guided Diffusion Model
- Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing
- FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation
- Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
- SnapMoGen: Human Motion Generation from Expressive Texts
- SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
- StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
- SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Decoupled Weight Decay Regularization
- Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
- Scalable Diffusion Models with Transformers
- TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis
- FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
- Neural Discrete Representation Learning
- MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
Related papers
- SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
- CADReasoner: Iterative Program Editing for CAD Reverse Engineering
- QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
- DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
- MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles
- MeshSplatBench: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering