publications
2024
- Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-JudgearXiv preprint arXiv:2407.19594, 2024
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder PipelinearXiv preprint arXiv:2406.11939, 2024
-
2023
-
- Statistical Inference on Multi-armed Bandits with Delayed FeedbackNov 2023
- A Reduction-based Framework for Sequential Decision Making with Delayed FeedbackarXiv preprint arXiv:2302.01477, Nov 2023
-
2022
- Nearly optimal policy optimization with stable at any time guaranteeIn International Conference on Machine Learning , Nov 2022
2021
- On reinforcement learning with adversarial corruption and its application to block mdpIn International Conference on Machine Learning , Nov 2021
- A unified framework for conservative explorationarXiv preprint arXiv:2106.11692, Nov 2021
2020
- Sanity-checking pruning methods: Random tickets can win the jackpotAdvances in neural information processing systems, Nov 2020