| 2024 | ICLR | The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry. | Michael Zhang, Kush Bhatia, Hermann Kumbong, Christopher R |
| 2023 | AISTATS | Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws. | Kush Bhatia, Wenshuo Guo, Jacob Steinhardt |
| 2023 | ICLR | Ask Me Anything: A simple strategy for prompting language models. | Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel J. Orr, Neel Guha, Kush Bhatia, Ines Chami, Christopher R |
| 2023 | ICLR | On the Sensitivity of Reward Inference to Misspecified Human Models. | Joey Hong, Kush Bhatia, Anca D. Dragan |
| 2022 | ICLR | The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. | Alexander Pan, Kush Bhatia, Jacob Steinhardt |
| 2022 | ICML | Congested Bandits: Optimal Routing via Short-term Resets. | Pranjal Awasthi, Kush Bhatia, Sreenivas Gollapudi, Kostas Kollias |
| 2019 | AISTATS | Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. | Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright |
| 2019 | COLT | Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression. | Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain |
| 2018 | IROS | Establishing Appropriate Trust via Critical States. | Sandy H. Huang, Kush Bhatia, Pieter Abbeel, Anca D. Dragan |