Advancing Robotics with Vision Language Action (VLA) Models | Prelim Exam Talk
What’s it like to give a preliminary exam (aka Area Exam) talk as a PhD student in robotics? In this video, I share my prelim exam presentation, where I introduce Vision-Language-Action (VLA) models and walk through their development in modern robotics. You’ll get a (mostly) chronological overview of how VLAs evolved—from early vision-language models to today’s cutting-edge action-generating systems. I break down several important papers, highlight why VLA research matters for embodied AI, and discuss some key papers and innovations in the field. If you’re interested in robotics, deep learning, embodied AI, or the PhD research process, this talk is a great starting point! 🔍 What you’ll learn - What Vision-Language-Action (VLA) models are - How VLAs differ from vision-language and policy-learning approaches - Key papers that shaped the trajectory of VLA research - Applications of VLAs in robot manipulation and decision-making - What a PhD prelim exam presentation is like Papers Discussed 1. B. Ichter et al., “Do As I Can, Not As I Say: Grounding Language in Robotic Affordances,” in Proc. 6th Conf. Robot Learning (CoRL), vol. 205, PMLR, Dec. 14–18, 2023, pp. 287–318. 2. A. Brohan et al., “RT-1: Robotics Transformer for Real-World Control at Scale,” in Proc. Robotics: Science & Systems (RSS), Jul. 2023, doi:10.15607/RSS.2023.XIX.025 3. Zitkovich, Brianna, et al. "Rt-2: Vision-language-action models transfer web knowledge to robotic control." Conference on Robot Learning. PMLR, 2023. 4. Kim, Moo Jin, et al. "OpenVLA: An Open-Source Vision-Language-Action Model." Conference on Robot Learning. PMLR, 2025. 5. Ghosh, Dibya, et al. "Octo: An Open-Source Generalist Robot Policy." Robotics: Science and Systems. 2024. 6. J. Wen et al. “DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control” Proceedings of The 9th Conference on Robot Learning, PMLR 305:3094-3114, 2025. 7. K. Black et al., “π₀: A Vision-Language-Action Flow Model for General Robot Control,” in Proc. Robotics: Science & Systems (RSS), Paper ID 10, Jun. 21, 2025. 8. K. Black et al., “π₀.5: A Vision-Language-Action Model with Open-World Generalization,” in Proc. 9th Conference on Robot Learning (CoRL), vol. 305, PMLR, Sept. 27-30, 2025, pp. 17-40. 9. L. X. Shi, et al., “Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models,” in Proc. Int. Conf. Machine Learning (ICML), Poster 44202, Jul. 17, 2025. 10. A. Cheng et al., “NaVILA: Legged Robot Vision-Language-Action Model for Navigation,” in Proc. Robotics: Science & Systems (RSS), Los Angeles, CA, USA, Jun. 21-25 2025. 11. Zhao, Qingqing, et al. "Cot-vla: Visual chain-of-thought reasoning for vision-language-action models." Proceedings of the Computer Vision and Pattern Recognition Conference. 2025. 12. Zawalski, Michał, et al. "Robotic Control via Embodied Chain-of-Thought Reasoning." Conference on Robot Learning. PMLR, 2025. #robotics #artificialintelligence #embodiedai #aiagents #ai #ml #machinelearning #gradstudents #gradstudentlife #phdstudent #phdjourney