vision language action

10 Open Challenges Steering the Future of Vision-Language-Action Models AAAI 2026 Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Models EACL 2026 DiTEA: Mixture-of-Experts for Vision-Language-Action Model in Robotic Manipulation AAAI 2026 FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning AAAI 2026 MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation AAAI 2026 MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming AAAI 2026 OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model AAAI 2026 SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation AAAI 2026 Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling AAAI 2026 Unlocking the Power of Large Multimodal Models for Robot Learning: Robustness, Generalization, and Opportunities AAAI 2026 DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression ICML 2025 FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Flow Models CoRL 2025 Foundation Models Meet Embodied Agents NAACL 2025 JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse ACL 2025 TrackVLA: Embodied Visual Tracking in the Wild CoRL 2025 Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks RSS 2025 UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent ICML 2025 VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation ICLR 2025 An Embodied Generalist Agent in 3D World ICML 2024