AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings

Theodor Westny, David Axelsson, Björn Olofsson, Erik Frisk

ECCV 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal 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
use KL divergence instead of L1, Wasserstein or MMD as dissimilarity (ablation)latent dataset embeddings · zero-shot transferSpearman rho: 0.482 (best alt.) -> 0.811Improved
use KL divergence instead of mean speed difference (ablation)latent dataset embeddings · zero-shot transferSpearman rho: 0.624 -> 0.811Improved
increase latent dim from 32 to 128 (ablation)embedding model · zero-shot transferSpearman rho: 0.811 -> 0.736Hurt
increase latent dim from 32 to 128 (ablation)embedding model · post-fine-tuning degradationSpearman rho: 0.729 -> 0.874Improved
use KL-based source selection instead of randomsource selection · zero-shot transfertop-3 rate: 13.2% -> 83.3%Improved
use KL-based selection instead of largest-source selectionsource selection · zero-shot transfermean absolute minADE6 gap: 0.984 -> 0.100Improved
pretrain on lower-KL source then fine-tune on ArgoverseQCNet · ArgoverseminADE6 after fine-tuningImproved
larger KL divergence between datasetsQCNet fine-tuning · forgetting on source datasetminADE6 change: rho=0.729Hurt
regularize covariance with alpha 1e-4 instead of 1e-7 (ablation)covariance estimator · L=32Spearman rho: 0.817 -> 0.811No 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