AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

DECODE: Domain-Aware Continual Domain Expansion for Motion Prediction

Boqi Li, Haojie Zhu, Henry X. Liu

TPAMI 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction

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 deep Bayesian uncertainty balancing of generalized and specialized models (ablation)DECODE after phase 1 · HighD minADEminADE: 65.87 -> 0.839Improved
add deep Bayesian uncertainty balancing (ablation)DECODE after phase 1 · InD minADEminADE: 1.984 -> 1.165Improved
add deep Bayesian uncertainty balancing (ablation)DECODE after phase 1 · RounD minADEminADE: 0.527 -> 0.531No clear effect
increase prior evidence e0 beyond its best value (ablation)DECODE · RounDminADE/minFDEHurt
increase prior evidence e0 (ablation)DECODE · HighD and InDminADE/minFDEImproved
use DECODE hypernetwork instead of rehearsal DER++(500)DECODE · motion prediction continual learningAER minADE: 0.598 -> 0.584Improved
use DECODE instead of DualPromptDECODE · motion prediction continual learningFGT minADE: 0.040 -> 0.044Mixed
replace regularization (EWC) with rehearsal (ER)baselines · motion prediction continual learningAER minADE: 2.038 -> 0.896Improved
place DualPrompt E-Prompts in encoder and decoder instead of encoder only (ablation)DualPrompt · motion predictionAER minADE: 0.794 -> 0.608Improved
place CODA-P prompts in decoder only instead of encoder+decoder (ablation)CODA-P · motion predictionAER minADE: 0.685 -> 0.647Improved
apply DECODE to ViT-B/16 on 5-datasets vs DualPromptDECODE · 5-datasetsaverage accuracy: 88.08 -> 90.56Improved
apply DECODE to ViT-B/16 on CIFAR-100 vs CODA-PDECODE · 10-task CIFAR-100average accuracy: 91.71 -> 86.41Hurt

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