Exploring Motion-Language Alignment for Text-driven Motion Generation
cs.CV
Submitted: 2026-04-03
Updated: 2026-10-10
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Why do LLMs attend to the first token?
- CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
- CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
- When Attention Sink Emerges in Language Models: An Empirical View
- MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation
- Classifier-Free Diffusion Guidance
- InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling
- MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
- Auto-Encoding Variational Bayes
- Flow Matching for Generative Modeling
- Flow Matching Guide and Code
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Absolute Coordinates Make Motion Generation Easy
- Attention Sinks in Diffusion Language Models
- Rectified-CFG++ for Flow Based Models
- Human Motion Diffusion as a Generative Prior
- Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
- Human Motion Diffusion Model
- CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models