AI Paper Atlas

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

ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction

Alen Mrdovic, Qingze Liu, Danrui Li, Mathew Schwartz, Kaidong Hu, Sejong Yoon, Mubbasir Kapadia, Vladimir Pavlovic

ECCV 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 0 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
add six-shot (best-of-K) training instead of one-shot (ablation)ECTraj · Argoverse 2 motion forecastingFDE6: 1.03 -> 0.96Improved
add six-shot (best-of-K) training instead of one-shot (ablation)ECTraj · Argoverse 2 motion forecastingADE6: 0.53 -> 0.50Improved
add fusion of ground truth with teacher output (ablation)ECTraj · Argoverse 2 motion forecastingFDE6: 0.99 -> 0.96Improved
add fusion of ground truth with teacher output (ablation)ECTraj · Argoverse 2 motion forecastingMR6: 0.14 -> 0.13Improved
fuse only midpoint/endpoint instead of full ground truth replacement (ablation)ECTraj · Argoverse 2 motion forecastingFDE6: 1.10 -> 0.96Improved
fuse only midpoint/endpoint instead of full ground truth replacement (ablation)ECTraj · Argoverse 2 motion forecastingADE6: 0.57 -> 0.50Improved
ECT timestep scheduling instead of ICT (ablation)ECTraj · Argoverse 2 motion forecastingFDE6: 1.02 -> 0.96Improved
ECT timestep scheduling instead of ICT (ablation)ECTraj · Argoverse 2 motion forecastingMR6: 0.15 -> 0.13Improved
best-of-K on diffusion with mode closest to data (ablation)OptTrajDiff · Argoverse 2 motion forecastingFDE6: 1.31 -> 1.17Improved
best-of-K on diffusion with mode closest to noise (ablation)OptTrajDiff · Argoverse 2 motion forecastingFDE6: 1.31 -> 1.42Hurt
replace diffusion denoiser with consistency model (1 step)ECTraj vs OptTrajDiff · Argoverse 2 motion forecastingGFLOPs: 1311 -> 132Improved
replace diffusion denoiser with consistency model (1 step)ECTraj vs OptTrajDiff · Argoverse 2 single-scenario latency (ms)denoising latency (ms): 29.71 -> 2.97Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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