Triangular Resampling for Long-Horizon Motion Generation
Quick summary
arXiv:2609.34697v2 Announce Type: replace-cross Abstract: We introduce Triangular Resampling (TR), a post-training method for mitigating long-horizon error accumulation in motion diffusion models. Built on FloodDiffusion's triangular denoising schedule, TR addresses the mismatch between ground-truth-derived training windows and model-generated inference states. Replacing only completed motion history leaves this mismatch unresolved in partially denoised states within the active window. TR therefore extends rollout-based training to these states, using ground-truth clamping to limit excessive d
Key takeaways
- arXiv:2609.34697v2 Announce Type: replace-cross Abstract: We introduce Triangular Resampling (TR), a post-training method for mitigating long-horizon error accumulation in motion diffusion models.
- Built on FloodDiffusion's triangular denoising schedule, TR addresses the mismatch between ground-truth-derived training windows and model-generated inference states.
- Replacing only completed motion history leaves this mismatch unresolved in partially denoised states within the active window.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments