Xingchen Wan
Xingchen Wan
Home
Featured
Publications
Tags
Experience
Contact
Light
Dark
Automatic
1
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Mitigating prompt biases and unifying existing calibration approaches
without
labeled data (ICLR 2024)
Han Zhou
,
Xingchen Wan
,
Lev Proleev
,
Diana Mincu
,
Jilin Chen
,
Katherine Heller
,
Subhrajit Roy
PDF
Cite
Google Research Blog
Abstract
OpenReview
Adaptive Batch Sizes for Active Learning: A Probabilistic Numerics Approach
International Conference on Artificial Intelligence and Statistics (AISTATS)
Masaki Adachi
,
Satoshi Hayakawa
,
Martin Jørgensen
,
Xingchen Wan
,
Vu Nguyen
,
Harald Oberhauser
,
Michael Osborne
PDF
Cite
Code
Abstract
Working Memory Capacity of ChatGPT: An Empirical Study
AAAI Conference on Artificial Intelligence (AAAI), 2024
Dongyu Gong
,
Xingchen Wan
,
Dingmin Wang
PDF
Cite
Code
Abstract
Universal Self-Adaptive Prompting
Empirical Methods in Natural Language Processing (EMNLP), 2023
Xingchen Wan
,
Ruoxi Sun
,
Hootan Nakhost
,
Hanjun Dai
,
Julian Martin Eisenschlos
,
Sercan Ö. Arık
,
Tomas Pfister
PDF
Cite
Google Research Blog
Abstract (Google Research)
OpenReview
ACL Anthology
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning
Orders-of-magnitude faster hard prompt search with SoTA performance (EMNLP Findings 2023)
Han Zhou
,
Xingchen Wan
,
Ivan Vulić
,
Anna Korhonen
PDF
Cite
Code
Abstract
OpenReview
ACL Anthology
Bayesian Optimisation of Functions on Graphs
Neural Information Processing Systems (NeurIPS), 2023
Xingchen Wan
,
Pierre Osselin
,
Henry Kenlay
,
Binxin Ru
,
Michael Osborne
,
Xiaowen Dong
PDF
Cite
Code
Abstract
OpenReview
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Findings of the Association for Computational Linguistics: ACL 2023
Xingchen Wan
,
Ruoxi Sun
,
Hanjun Dai
,
Sercan Ö. Arık
,
Tomas Pfister
PDF
Cite
Google Research Blog
Abstract (Google Research)
ACL Anthology
Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization
Neural Information Processing Systems (NeurIPS), 2022
Samuel Daulton
,
Xingchen Wan
,
David Eriksson
,
Maximilian Balandat
,
Michael Osborne
,
Eytan Bakshy
PDF
Cite
Code
Abstract (Meta Research)
OpenReview
Slides & Talk
Bayesian Generational Population-Based Training
International Conference on Automated Machine Learning (AutoML-Conf), 2022
Xingchen Wan
,
Cong Lu
,
Jack Parker-Holder
,
Philip J. Ball
,
Vu Nguyen
,
Binxin Ru
,
Michael Osborne
PDF
Cite
Code
OpenReview
Slides & Talk
AutoML Seminars
On Redundancy and Diversity in Cell-based Neural Architecture Search
International Conference on Learning Representations (ICLR), 2022.
Xingchen Wan
,
Binxin Ru
,
Pedro M. Esperança
,
Zhenguo Li
PDF
Cite
Code
OpenReview
Slides
»
Cite
×