AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

Rethinking Training and Inference for Trajectory Forecasting: Linking Winner-Take-All back to GMMs

Qiyuan Wu, Katie Luo, Bharath Hariharan, Wei-Lun Chao, Mark Campbell

ECCV 2026 · Large language models › Reasoning and chain of thought · approach: Test-time compute scaling

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
replace greedy selection with test-time weighted mergingWayformer · NuScenes Prediction (M=5)minFDE5: 8.287 -> 3.050Improved
replace greedy selection with test-time weighted mergingMTR-e2e · NuScenes Prediction (M=5)minFDE5: 5.369 -> 2.848Improved
replace greedy selection with test-time weighted mergingWayformer · Waymo Open Motion (M=5)minFDE5: 10.994 -> 4.968Improved
replace NMS with mergingMTR-e2e · NuScenes Prediction (M=5)miss rate5: 0.521 -> 0.535Mixed
replace merging with direct training of 5 modesWayformer · NuScenes Prediction (M=5)minFDE5: 3.050 -> 2.976Improved
replace merging with direct trainingMTR-e2e · NuScenes Prediction (M=5)minFDE5: 2.848 -> 2.938Hurt
add one-step EM finetuning of mode probabilities before greedy selectionWayformer · NuScenes Prediction (M=5)minFDE5: 8.287 -> 5.702 (-31%)Improved
add one-step EM finetuning before NMSMTR-e2e · NuScenes Prediction (M=5)minFDE5: 4.440 -> 3.752 (-15%)Improved
add one-step EM finetuning before greedy selectionWayformer · Waymo Open Motion (M=5)minFDE5: 10.994 -> 10.370 (-5.7%)Improved
add one-step EM finetuning before greedy selectionWayformer · Waymo Open Motion (M=5)miss rate5: 0.695 -> 0.757Hurt
add one-step EM finetuningWayformer · NuScenes Prediction (M=5)top-5 NLL: 4404.5 -> 1796.4 (-59%)Improved
add one-step EM finetuningMTR-e2e · NuScenes Prediction (M=5)top-1 NLL: 792.9 -> 777.0 (-2.0%)No 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