Kyle Stachowicz
8 papers · 2023–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (2) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)
👥
Mega-Team
(35)
Conferences
CORL (6)
RSS (2)
Top co-authors
Keywords
deep reinforcement learning
(1)
visual observation
(1)
robotic navigation
(1)
epistemic uncertainty
(1)
autonomous driving
(1)
autoregressive model
(1)
foundation model
(1)
mobile robot
(1)
risk-sensitive control
(1)
discrete cosine transform
(1)
prompt tuning
(1)
vision-language-action model
(1)
sample-efficient learning
(1)
safe exploration
(1)
off-road driving
(1)
visual navigation transformer
(1)
diffusion-based goal proposal
(1)
mobile robotics
(1)
action tokenization
(1)
action space curriculum
(1)
Papers
FAST: Efficient Action Tokenization for Vision-Language-Action Models
RSS 2025
$\pi_0.5$: a Vision-Language-Action Model with Open-World Generalization
CORL 2025
Lifelong Autonomous Improvement of Navigation Foundation Models in the Wild
CORL 2024
Learning Robotic Locomotion Affordances and Photorealistic Simulators from Human-Captured Data
CORL 2024
SELFI: Autonomous Self-Improvement with RL for Vision-Based Navigation around People
CORL 2024
RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes
RSS 2024
FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing
CORL 2023
ViNT: A Foundation Model for Visual Navigation
CORL 2023