CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models
2026-07-06 • Robotics
Robotics
AI summaryⓘ
The authors present CAC-VLA, a new method that helps robots use visual and language cues more effectively to perform tasks. Instead of creating detailed action plans, their system teaches the robot to predict simple, layered action hints that guide precise movements. This approach works within the existing model and adjusts how much these hints influence the robot's actions. Tests show that CAC-VLA improves task success rates on two robot manipulation benchmarks, making it easier for robots to connect understanding with motor control.
Vision-Language-Action modelsrobot manipulationlatent actionscontext gatingaction conditioningvisual-language representationsmotor controlLIBERO datasetcontinuous action generation
Authors
Yifu Xiong, Wenhao Yu, Jiaxuan Lin, Bojun Zou, Jiahao Li, Lu Zhang, Yanyong Zhang, Jianmin Ji
Abstract
Vision-Language-Action (VLA) models have become a promising paradigm for generalist robot manipulation, where visual-language representations are used to condition continuous action generation. However, these representations are not explicitly optimized for action conditioning, leaving the action expert to bridge the gap between multimodal understanding and precise motor control. Recent action-reasoning methods introduce additional modules to generate explicit action plans or action-space reasoning signals, demonstrating the benefit of action-level guidance but often requiring separate action-generation frameworks. We propose CAC-VLA, a Context-Gated Action Conditioning framework that learns a lightweight latent-action interface directly within the VLM. Instead of generating executable trajectories, CAC-VLA trains the VLM to predict coarse-to-fine latent actions, which are structured representations encoded from future action segments, and adaptively leverages them to condition the action expert via a context gate. This enables VLM-native action conditioning while calibrating the influence of latent-action guidance on expert action generation. Experiments on LIBERO and LIBERO-Plus demonstrate the effectiveness of CAC-VLA, achieving 98.3% average success rate on LIBERO and 89.5% LIBERO-Plus, suggesting that context-gated latent-action conditioning is an effective interface for continuous expert control.