TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control
cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Project page: https://vkgo.github.io/TACD
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
- pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
- Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
- MoGeFlow: Flowing Through Motion Codebook Geometry for Text-to-Motion Generation
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- Mean Flows for One-step Generative Modeling
- BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
- AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
- Prediction--Loss Alignment for Sampler--Robust Flow Matching Training
- Efficient Text-driven Motion Generation via Latent Consistency Training
- MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
- MotionHiFlow: Text-to-motion via hierarchical flow matching
- Back to Basics: Let Denoising Generative Models Denoise
- IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- On-Policy Adversarial Flow Distillation for Autoregressive Video Generation
- Learning Few-Step Diffusion Models by Trajectory Distribution Matching
- Absolute Coordinates Make Motion Generation Easy
- Kimodo: Scaling Controllable Human Motion Generation
- Multistep Distillation of Diffusion Models via Moment Matching
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems