cd /news/artificial-intelligence/corelate-coordinated-human-object-mo… · home › topics › artificial-intelligence › article
[ARTICLE · art-173029] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

CoRelate: Coordinated Human-Object Motion Synthesis through Interaction Relations

A research team introduced CoRelate, a diffusion framework that coordinates full-body human-object motion synthesis through explicit hand-part interaction relations and task feedback for rigid and articulated objects, detailed in arXiv paper 2611.25166v1. CoRelate specifies the participating hand, its part-relative reference position and participation interval as generation conditions and as references for measuring interaction realization, with a jointly trained temporal refiner updating human and object motion at each denoising step. Experiments showed improved object-goal satisfaction, contact F1 and complete interaction success over evaluated baselines, with ablations supporting relation conditioning and complementary task and relation feedback.

key takeaway

Conditioning a diffusion model on explicit hand-part relations (participating hand, part-relative reference position, participation interval) plus task residuals at each denoising step improved object-goal satisfaction, contact F1 and complete interaction success over evaluated baselines.

by read1 min views1 publishedNov 20, 2026

arXiv:2611.25166v1 Announce Type: new Abstract: Human-object motion synthesis requires coordinated human participation as objects move toward specified goals. However, reaching object targets does not ensure that contact is established and maintained, while adjustments that improve contact may interfere with task completion. We introduce CoRelate, a diffusion framework that coordinates full-body human-object motion through explicit interaction relations and task feedback for rigid and articulated objects. We represent intended participation through hand-part relations that specify the participating hand, its part-relative reference position, and participation interval. These relations serve both as generation conditions and as references for measuring interaction realization. At each denoising step, a temporal refiner trained jointly with the generator combines relation deviations, task residuals, and motion features from the current prediction to jointly update human and object motion across the sequence. After generation, temporal motion correction addresses remaining contact failures by optimizing local motion segments while preserving object trajectories and protected human motion. Experiments demonstrate improved object-goal satisfaction, contact F1, and complete interaction success over the evaluated baselines. Ablation studies support the benefits of relation conditioning and the complementary roles of task and relation feedback.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @corelate 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/corelate-coordinated…] indexed:0 read:1min 2026-11-20 · —