AI Paper Atlas

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

FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation

Cui Miao, Tao Chang, Meihan Wu, Hongbin Xu, Chun Li, Ming Li, Xiaodong Wang

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 15 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 Instruction-Oriented Scene-Parsing (IOSP) (ablation)FedVLA · Real-world UR3 (average)success rate (%): 41.1 -> 63.3Improved
add IOSP (ablation)FedVLA · Real-world UR3 (Trash Collection)success rate (%): 13.3 -> 46.7Improved
add Dual Gating MoE instead of standard FFN (ablation)FedVLA · Real-world UR3 (average)success rate (%): 31.7 -> 63.3Improved
add DGMoE instead of standard FFN (ablation)FedVLA · Real-world UR3 (Clean Up)success rate (%): 20.0 -> 53.3Improved
add Expert-Driven Aggregation instead of FedAvg aggregation (ablation)FedVLA · Real-world UR3 (average)success rate (%): 26.7 -> 63.3Improved
use FedVLA instead of FedAvgFedAvg · Meta-World simulation (average)success rate (%): 51.7 -> 63.3Improved
use FedVLA instead of FedAvgFedAvg · Real-world UR3 (average)success rate (%): 53.3 -> 63.3Improved
federated FedVLA instead of centralized trainingCentralized · Meta-World simulation (average)success rate (%): 65.0 -> 63.3No clear effect
federated FedVLA instead of centralized trainingCentralized · Real-world UR3 (average)success rate (%): 63.4 -> 63.3No clear effect
federated FedVLA instead of centralized trainingCentralized · Meta-World simulation (Close Drawer)success rate (%): 73.3 -> 80.0Improved
federated FedVLA instead of centralized trainingCentralized · Meta-World simulation (Door Lock)success rate (%): 86.7 -> 80.0Hurt
use dual-gating DGMoE instead of fixed top-k MoEFedVLA · Real-world UR3avg activated experts per token: 1.219, 1.229, 1.225, 1.227Improved

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