AI Paper Atlas

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

TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size

Stefan Lionar, Gim Hee Lee

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
single unified transformer policy with teammate tokens trained on 2-8 agents instead of team-size-specific policyCooHOI* · Cooperative carrying, 8 agentssuccess rate (%): 61.5 -> 97.5Improved
unified policy vs best matched team-size baselineCooHOI*-2 · Cooperative carrying, 2 agentssuccess rate (%): 97.5 -> 99.1Improved
unified policy with learned formation vs pre-defined oracle contact pointsCooHOI*-4 · Cooperative carrying, 4 agentssuccess rate (%): 94.5 -> 99.2Improved
unified policy under 5x heavy load, 8 agentsCooHOI*-4 · Cooperative carrying 5x load, 8 agentssuccess rate (%): 14.2 -> 81.1Improved
TeamHOI vs CooHOI*-8 on motion smoothness at 8 agentsCooHOI*-8 · Cooperative carrying, 8 agentsmean absolute jerk (m/s3): 45.2 -> 34.2Improved
TeamHOI vs CooHOI*-4 on 4-agent cooperative time ratioCooHOI*-4 · Cooperative carrying, 4 agentscooperative time ratio (%): 92.1 -> 96.1Improved
add masked AMP (ablation)TeamHOI · Walking+formation+liftingtask rewardImproved
add principal-axes coverage reward to angular spread reward (ablation)TeamHOI · Cooperative carryingformation qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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