AI Paper Atlas

Research map / Continual learning / Online and replay-based

Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment

Fanqi Yu, Matteo Tiezzi, Tommaso Apicella, Cigdem Beyan, Vittorio Murino

CVPR 2026 · Continual learning › Online and replay-based · approach: Plasticity-preserving continual reinforcement learning · 1 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 IFA loss on top of latent replay (ablation)MLR · LIBERO-OBJECTAUC: 77.6 -> 79.4Improved
add IFA loss on top of latent replay (ablation)MLR · LIBERO-GOALAUC: 74.6 -> 77.2Improved
add IFA loss on top of latent replay (ablation)MLR · LIBERO-50AUC: 54.7 -> 56.1Improved
add IFA loss on top of latent replay (ablation)MLR · LIBERO-OBJECTNBT: 12.3 -> 11.4No clear effect
select IFA pairs by language + agent-view similarity instead of language + action (ablation)MLR + IFA · LIBERO-OBJECTAUC: 75.1 -> 79.4Improved
use top 50% of task pairs instead of 66.6% (ablation)MLR + IFA · LIBERO-OBJECTAUC: 75.8 -> 79.4Improved
use language embedding as reference instead of mean global latent (ablation)MLR + IFA · LIBERO-GOALAUC: 70.5 -> 77.2Improved
store features with probability 0.50 instead of 0.10 (ablation)MLR + IFA · LIBERO-GOALAUC: 66.2 -> 77.2Improved
store features with probability 0.50 instead of 0.20 (ablation)MLR + IFA · LIBERO-GOALAUC: 77.4 -> 77.2No clear effect
use angular distance instead of cosine distance in IFA loss (ablation)MLR + IFA · LIBERO-OBJECT and LIBERO-GOALFWT, NBT, AUCImproved
replay latent features instead of raw trajectories, frozen CLIPMLR · LIBERO-GOALAUC: 60.5 -> 74.6Improved

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