SJTU and Alibaba Introduce LA4VLA: Decoupling Language-Action to Boost Robot Policies
青稞AI · wechat · 2026-08-03
To address the issue of Vision-Language-Action (VLA) models over-relying on visual shortcuts and weakening language constraints, Shanghai Jiao Tong University and Alibaba introduced LA4VLA. This method temporarily removes visual input during the pre-training phase, allowing the model to focus exclusively on learning the correspondence between language and actions.
By decoupling language-action learning from visual grounding, the researchers constructed a 33K vision-agnostic dataset. Experiments demonstrate that this explicit language-action pre-training serves as an effective complementary signal to standard VLA training, significantly improving policy performance and robustness against visual perturbations in embodied robotics.
More from Embodied
- Peking University's SimForcing distills simulation motion priors into robot world models — PekingUniversity · 2026-10-16
- NVIDIA and Mercedes-Benz Expand Partnership on Next-Gen Automated Driving — nvidia · 2026-10-16
- ~25,000 Humanoid Robots Shipped in H1 2026, Over 95% from Chinese Vendors — ingliguori · 2026-10-16
- openpilot brings stoplight-stopping autonomy to a 2019 Corolla — k7agar · 2026-10-16
- Hironobu Fujiyoshi publishes deck: from AI agents to Agentic Robotics — HirokatuKataoka · 2026-10-16
- CoDA co-evolves simulation and robot policies via shared failure memory, lifting OOD success from 5.3% to 27.6% — PLAN-Lab · 2026-10-16