HiST-VLA: A Hierarchical Spatio-Temporal Vision-Language-Action Model for Embodied and Interpretable Autonomous Driving
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 10932-10940
Abstract
No abstract availableThis publication has 12 references indexed in Scilit:
- π₀: A Vision-Language-Action Flow Model for General Robot Control2025
- DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving2025
- SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment2025
- CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving2025
- Improved Baselines with Visual Instruction Tuning2024
- VLP: Vision Language Planning for Autonomous Driving2024
- VAD: Vectorized Scene Representation for Efficient Autonomous Driving2023
- Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers2023
- Urban Driving with Conditional Imitation Learning2020
- Deep Residual Learning for Image Recognition2016