AI Paper Atlas

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

FT-NCFM: An Influence-Aware Data Distillation Framework for Efficient VLA Models

Kewei Chen, Yayu Long, Shuai Li, Mingsheng Shang

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 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 contrastive verification refinement to influence weights (ablation)FT-NCFM (5% data) · CALVIN ABC->DAvg. Len: 2.81 -> 3.11Improved
add FT influence engine instead of random weights (ablation)FT-NCFM (5% data) · CALVIN ABC->DAvg. Len: 2.15 -> 3.11Improved
synthesize coreset with FT-NCFM instead of random sampling at 5%VLA training data · CALVIN ABC->DAvg. Len: 1.88 -> 3.11Improved
synthesize coreset with FT-NCFM instead of influence-function selection at 5%VLA training data · CALVIN ABC->DAvg. Len: 2.45 -> 3.11Improved
increase synthetic data ratio from 1% to 10% (ablation)FT-NCFM · LIBERO (avg of 4 suites)success rate (%): 46.9 -> 74.2Improved
data distillation (10%) instead of policy distillation on full dataVLA training · CALVIN ABC->DAvg. Len / training time: 3.20 -> 3.47 Avg. Len; 178 -> 31.5 GPU-hImproved
train on 10% distilled data versus full dataFT-NCFM vs SpatialVLA · LIBERO (avg of 4 suites)success rate (%): 78.1 -> 74.2Hurt

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