AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

Minh Duc Nguyen, Nghiem Tuong Diep, Nguyen Gia Binh, Trong-Bao Ho, Doanh Le Thien, Quang Tan Nguyen, Thien-Loc Ha, Tran Van Nhiem, Bao Thach, Tran Xuan Nhat, Tuan Anh Tran, Artur Habuda and 11 more

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 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 FOCA future-oriented conditioning to pi0 with 10% demospi0 · LIBERO avg, 10% demossuccess rate (%): 77.6 -> 85.3Improved
add FOCA at 40% demos versus pi0 at 100% demospi0 · LIBERO avgsuccess rate (%): 94.0 vs 94.6Improved
use PEFT methods (LoRA, DoRA, Control-VLA) instead of FOCApi0 · LIBERO avg, 10% demossuccess rate (%): 77.6 (pi0) vs 78.2-78.6No clear effect
add pseudo-actions from inverse generative modeling on DreamGen videospi0 · LIBERO avg, 10% demossuccess rate (%): 77.6 -> 76.8Hurt
pretrain implicit objective on DreamGen synthetic videos before co-training (ablation)FOCA implicit · LIBERO avg, 40% demossuccess rate (%): 96.6 -> 98.0Improved
add explicit future prediction on top of implicit alignment (ablation)FOCA · LIBERO avg, 10% demossuccess rate (%): 83.6 -> 85.3Improved
use latent object-centric prediction instead of pixel-level prediction (ablation)FOCA explicit · LIBERO avg, 40% demossuccess rate (%): 91.4 -> 93.3Improved
change number of explicit tokens from 8 to 2 or 18 (ablation)FOCA explicit · LIBERO avg, 10% demossuccess rate (%): 79.2 -> 76.6 (2 tokens), 76.4 (18 tokens)Hurt
align to multiple future frames instead of a single frame (ablation)FOCA implicit · LIBERO avg, 10% demossuccess rate (%): 83.6 -> 83.3No clear effect
use object-centric rather than full-image embeddings for implicit alignment (ablation)FOCA implicit · LIBERO avg, 10% demossuccess rate (%): 81.7 -> 83.6Improved
use adaptive (visual-feature) token initialization instead of random (ablation)FOCA · LIBERO avg, 40% demossuccess rate (%): 91.7 -> 94.3Improved
use FOCA instead of FLARE conditioningGR00T-N1.5 · RoboCasa 5 tasks, 100 demosavg success rate (%): 28.4 -> 34.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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