vision-language-action model

Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control ICCV 2025 SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters CVPR 2025 SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models RSS 2025 Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025 VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks ICCV 2025 VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers ICCV 2025 HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers CoRL 2024 HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid NeurIPS 2024 OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents NeurIPS 2024 OpenVLA: An Open-Source Vision-Language-Action Model CoRL 2024 Robotic Control via Embodied Chain-of-Thought Reasoning CoRL 2024 RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control CoRL 2023