دنبال کردن
Katie Kang
Katie Kang
UC Berkeley
ایمیل تأیید شده در berkeley.edu - صفحهٔ اصلی
عنوان
نقل شده توسط
نقل شده توسط
سال
Generalization through simulation: Integrating simulated and real data into deep reinforcement learning for vision-based autonomous flight‏
K Kang, S Belkhale, G Kahn, P Abbeel, S Levine‏
2019 international conference on robotics and automation (ICRA), 6008-6014, 2019‏
1682019
Unfamiliar finetuning examples control how language models hallucinate‏
K Kang, E Wallace, C Tomlin, A Kumar, S Levine‏
arXiv preprint arXiv:2403.05612, 2024‏
352024
Multi-task imitation learning for linear dynamical systems‏
TT Zhang, K Kang, BD Lee, C Tomlin, S Levine, S Tu, N Matni‏
Learning for Dynamics and Control Conference, 586-599, 2023‏
262023
Lyapunov density models: Constraining distribution shift in learning-based control‏
K Kang, P Gradu, JJ Choi, M Janner, C Tomlin, S Levine‏
International Conference on Machine Learning, 10708-10733, 2022‏
242022
Deep neural networks tend to extrapolate predictably‏
K Kang, A Setlur, C Tomlin, S Levine‏
The Twelfth International Conference on Learning Representations, 2024‏
72024
Hierarchically integrated models: Learning to navigate from heterogeneous robots‏
K Kang, G Kahn, S Levine‏
Conference on Robot Learning, 2021‏
62021
What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?‏
K Kang, A Setlur, D Ghosh, J Steinhardt, C Tomlin, S Levine, A Kumar‏
arXiv preprint arXiv:2411.07681, 2024‏
32024
Self-Improving Foundation Models Without Human Supervision‏
A Setlur, K Kang, A Kumar, F Behbahani, R Raileanu, R Agarwal‏
ICLR 2025 Workshop Proposals, 0‏
سیستم در حال حاضر قادر به انجام عملکرد نیست. بعداً دوباره امتحان کنید.
مقاله‌ها 1–8