Xingchen Wan

60 papers A* 14A 3Journal 39Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Can Large Language Models Generalize Procedures Across Representations?
CoRR
Fangru Lin, Valentin Hofmann, Xingchen Wan, Weixing Wang, Zifeng Ding, Anthony G. Cohn, Janet B. Pierrehumbert
2025 J jnl
Agentic Policy Optimization via Instruction-Policy Co-Evolution.
CoRR
Han Zhou, Xingchen Wan, Ivan Vulic, Anna Korhonen
2025 — conf
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models.
ACL (1)
Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan Ö. Arik
2025 J jnl
DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling.
CoRR
Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan Ö. Arik
2025 A* conf
From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation.
ICLR
Xingchen Wan, Han Zhou, Ruoxi Sun, Sercan Ö. Arik
2025 J jnl
From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation.
CoRR
Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Sercan Ö. Arik
2025 J jnl
Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration.
CoRR
Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Rajarishi Sinha, Sercan Ö. Arik
2025 J jnl
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies.
CoRR
Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulic, Anna Korhonen, Sercan Ö. Arik
2025 J jnl
Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL.
CoRR
Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun, Xingchen Wan, Hailong Li, Azalia Mirhoseini, Amin Saberi, Sercan Ö. Arik
2025 J jnl
VISTA: A Test-Time Self-Improving Video Generation Agent.
CoRR
Do Xuan Long, Xingchen Wan, Hootan Nakhost, Chen-Yu Lee, Tomas Pfister, Sercan Ö. Arik
2025 J jnl
Visual Planning: Let's Think Only with Images.
CoRR
Yi Xu, Chengzu Li, Han Zhou, Xingchen Wan, Caiqi Zhang, Anna Korhonen, Ivan Vulic
2024 A conf
Adaptive Batch Sizes for Active Learning: A Probabilistic Numerics Approach.
AISTATS
Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Xingchen Wan, Vu Nguyen, Harald Oberhauser, Michael A. Osborne
2024 J jnl
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models.
CoRR
Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan Ö. Arik
2024 J jnl
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning.
Trans. Assoc. Comput. Linguistics
Han Zhou, Xingchen Wan, Ivan Vulic, Anna Korhonen
2024 A* conf
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering.
ICLR
Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine A. Heller, Subhrajit Roy
2024 A* conf
Bayesian Optimization of Functions over Node Subsets in Graphs.
NeurIPS
Huidong Liang, Xingchen Wan, Xiaowen Dong
2024 J jnl
Bayesian Optimization of Functions over Node Subsets in Graphs.
CoRR
Huidong Liang, Xingchen Wan, Xiaowen Dong
2024 A* conf
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments.
EMNLP
Han Zhou, Xingchen Wan, Yinhong Liu, Nigel Collier, Ivan Vulic, Anna Korhonen
2024 J jnl
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments.
CoRR
Han Zhou, Xingchen Wan, Yinhong Liu, Nigel Collier, Ivan Vulic, Anna Korhonen
2024 J jnl
Iterate Averaging in the Quest for Best Test Error.
J. Mach. Learn. Res.
Diego Granziol, Nicholas P. Baskerville, Xingchen Wan, Samuel Albanie, Stephen Roberts
2024 A* conf
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization.
NeurIPS
Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Sercan Ö. Arik
2024 J jnl
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization.
CoRR
Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Sercan Ö. Arik
2024 A* conf
UQE: A Query Engine for Unstructured Databases.
NeurIPS
Hanjun Dai, Bethany Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans
2024 J jnl
UQE: A Query Engine for Unstructured Databases.
CoRR
Hanjun Dai, Bethany Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans
2024 A* conf
Working Memory Capacity of ChatGPT: An Empirical Study.
AAAI
Dongyu Gong, Xingchen Wan, Dingmin Wang
2023 J jnl
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning.
CoRR
Han Zhou, Xingchen Wan, Ivan Vulic, Anna Korhonen
2023 J jnl
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering.
CoRR
Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine A. Heller, Subhrajit Roy
2023 A* conf
Bayesian Optimisation of Functions on Graphs.
NeurIPS
Xingchen Wan, Pierre Osselin, Henry Kenlay, Binxin Ru, Michael A. Osborne, Xiaowen Dong
2023 J jnl
Bayesian Optimisation of Functions on Graphs.
CoRR
Xingchen Wan, Pierre Osselin, Henry Kenlay, Binxin Ru, Michael A. Osborne, Xiaowen Dong
2023 J jnl
Bayesian Quadrature for Neural Ensemble Search.
CoRR
Saad Hamid, Xingchen Wan, Martin Jørgensen, Binxin Ru, Michael A. Osborne
2023 J jnl
Bayesian Quadrature for Neural Ensemble Search.
Trans. Mach. Learn. Res.
Saad Hamid, Xingchen Wan, Martin Jørgensen, Binxin Ru, Michael A. Osborne
2023 — conf
Better Zero-Shot Reasoning with Self-Adaptive Prompting.
ACL (Findings)
Xingchen Wan, Ruoxi Sun, Hanjun Dai, Sercan Ö. Arik, Tomas Pfister
2023 J jnl
Better Zero-Shot Reasoning with Self-Adaptive Prompting.
CoRR
Xingchen Wan, Ruoxi Sun, Hanjun Dai, Sercan Ö. Arik, Tomas Pfister
2023 J jnl
Domain-Agnostic Batch Bayesian Optimization with Diverse Constraints via Bayesian Quadrature.
CoRR
Masaki Adachi, Satoshi Hayakawa, Xingchen Wan, Martin Jørgensen, Harald Oberhauser, Michael A. Osborne
2023 J jnl
SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning.
CoRR
Xinghui Li, Kai Han, Xingchen Wan, Victor Adrian Prisacariu
2023 — conf
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning.
EMNLP (Findings)
Han Zhou, Xingchen Wan, Ivan Vulic, Anna Korhonen
2023 J jnl
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning.
CoRR
Han Zhou, Xingchen Wan, Ivan Vulic, Anna Korhonen
2023 A* conf
Universal Self-Adaptive Prompting.
EMNLP
Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Hanjun Dai, Julian Eisenschlos, Sercan Ö. Arik, Tomas Pfister
2023 J jnl
Universal Self-adaptive Prompting.
CoRR
Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Hanjun Dai, Julian Martin Eisenschlos, Sercan Ö. Arik, Tomas Pfister
2022 A conf
Approximate Neural Architecture Search via Operation Distribution Learning.
WACV
Xingchen Wan, Binxin Ru, Pedro M. Esperança, Fabio Maria Carlucci
2022 A conf
BOiLS: Bayesian Optimisation for Logic Synthesis.
DATE
Antoine Grosnit, Cédric Malherbe, Rasul Tutunov, Xingchen Wan, Jun Wang, Haitham Bou-Ammar
2022 — conf
Bayesian Generational Population-Based Training.
AutoML
Xingchen Wan, Cong Lu, Jack Parker-Holder, Philip J. Ball, Vu Nguyen, Binxin Ru, Michael A. Osborne
2022 J jnl
Bayesian Generational Population-Based Training.
CoRR
Xingchen Wan, Cong Lu, Jack Parker-Holder, Philip J. Ball, Vu Nguyen, Binxin Ru, Michael A. Osborne
2022 A* conf
Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization.
NeurIPS
Samuel Daulton, Xingchen Wan, David Eriksson, Maximilian Balandat, Michael A. Osborne, Eytan Bakshy
2022 J jnl
Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization.
CoRR
Samuel Daulton, Xingchen Wan, David Eriksson, Maximilian Balandat, Michael A. Osborne, Eytan Bakshy
2022 J jnl
Estimation of Reference Voltages for Time-Difference Electrical Impedance Tomography.
IEEE Trans. Instrum. Meas.
Hao Yu, Xingchen Wan, Zhongxu Dong, Zhixi Zhang, Jiabin Jia
2022 A* conf
On Redundancy and Diversity in Cell-based Neural Architecture Search.
ICLR
Xingchen Wan, Binxin Ru, Pedro M. Esperança, Zhenguo Li
2022 J jnl
On Redundancy and Diversity in Cell-based Neural Architecture Search.
CoRR
Xingchen Wan, Binxin Ru, Pedro M. Esperança, Zhenguo Li
2021 J jnl
Adversarial Attacks on Graph Classification via Bayesian Optimisation.
CoRR
Xingchen Wan, Henry Kenlay, Binxin Ru, Arno Blaas, Michael A. Osborne, Xiaowen Dong
2021 A* conf
Adversarial Attacks on Graph Classifiers via Bayesian Optimisation.
NeurIPS
Xingchen Wan, Henry Kenlay, Robin Ru, Arno Blaas, Michael A. Osborne, Xiaowen Dong
2021 J jnl
Approximate Neural Architecture Search via Operation Distribution Learning.
CoRR
Xingchen Wan, Binxin Ru, Pedro M. Esperança, Fabio Maria Carlucci
2021 J jnl
BOiLS: Bayesian Optimisation for Logic Synthesis.
CoRR
Antoine Grosnit, Cédric Malherbe, Rasul Tutunov, Xingchen Wan, Jun Wang, Haitham Bou-Ammar
2021 A* conf
Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels.
ICLR
Bin Xin Ru, Xingchen Wan, Xiaowen Dong, Michael A. Osborne
2021 A* conf
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces.
ICML
Xingchen Wan, Vu Nguyen, Huong Ha, Bin Xin Ru, Cong Lu, Michael A. Osborne
2021 J jnl
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces.
CoRR
Xingchen Wan, Vu Nguyen, Huong Ha, Bin Xin Ru, Cong Lu, Michael A. Osborne
2020 J jnl
Explaining the Adaptive Generalisation Gap.
CoRR
Diego Granziol, Samuel Albanie, Xingchen Wan, Stephen J. Roberts
2020 J jnl
Iterate Averaging Helps: An Alternative Perspective in Deep Learning.
CoRR
Diego Granziol, Xingchen Wan, Stephen Roberts
2020 J jnl
Neural Architecture Search using Bayesian Optimisation with Weisfeiler-Lehman Kernel.
CoRR
Bin Xin Ru, Xingchen Wan, Xiaowen Dong, Michael A. Osborne
2020 J jnl
Sentiment Diffusion in Financial News Networks and Associated Market Movements.
CoRR
Xingchen Wan, Jie Yang, Slavi Marinov, Jan-Peter Calliess, Stefan Zohren, Xiaowen Dong
2019 J jnl
MLRG Deep Curvature.
CoRR
Diego Granziol, Xingchen Wan, Timur Garipov, Dmitry P. Vetrov, Stephen Roberts