AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

SyncMos: Scalable Motion Synchronisation for Multi-Agent Scene Interaction

Lingxiao Li, Dongwon Kim, Lingyan Ruan, Bin Chen, Taesoo Kwon, Taehyun Rhee

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use dependency-aware story planner instead of Event-Driven Storytelling baselineLLM event planner (Qwen-3-235B) · Synchronisation test setDependency accuracy (%): 68.4 -> 89.9Improved
use dependency-aware story planner instead of baselineLLM event planner (GPT-4o) · Dependency test setScenario pass rate (%): 0.0 -> 80.0Improved
use dependency-aware story planner instead of baselineLLM event planner (GPT-4o) · Dependency test setDependency accuracy (%): 20.5 -> 96.9Improved
use dependency-aware planner with small or mini backboneGPT-4o-mini planner · Synchronisation test setDependency accuracy (%): 71.4 -> 67.2Hurt
use dependency-aware planner with Qwen-3-8BQwen-3-8B planner · Synchronisation test setScenario pass rate (%): 26.7 -> 26.7No clear effect
use proposed planner when number of events growsplanner token usage · Dependency scenariosToken usageImproved
add time-warping plus diffusion posterior sampling refinement to LINGOLINGO · Grasp timing control (+-0.5 to +-1.5 s)Success rate (%): 0.0 -> 84.7 (+0.5 s)Improved
increase negative timing offset to -1.5 s (ablation)SyncMos synchronisation module · Grasp timing controlSuccess rate (%): 88.0 (-0.5 s) -> 37.3 (-1.5 s)Hurt
increase number of agents in handover chain from 2 to 10 (ablation)SyncMos full pipeline · Chained handover, House and Restaurant scenesTemporal synchronisation errorNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy