Jean-Francois Ton

41 papers A* 17A 2Journal 21Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration. ICLR Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu
2025	A*	`conf`	Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment. ICML Yunyi Shen, Hao Sun, Jean-Francois Ton
2025	J	`jnl`	How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs. CoRR Andrew Estornell, Jean-Francois Ton, Muhammad Faaiz Taufiq, Hang Li
2025	A*	`conf`	Rethinking Reward Modeling in Preference-based Large Language Model Alignment. ICLR Hao Sun, Yunyi Shen, Jean-Francois Ton
2025	J	`jnl`	Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs. CoRR Hao Sun, Yunyi Shen, Jean-Francois Ton, Mihaela van der Schaar
2025	A*	`conf`	Understanding Chain-of-Thought in LLMs through Information Theory. ICML Jean-Francois Ton, Muhammad Faaiz Taufiq, Yang Liu
2024	J	`jnl`	ACC-Debate: An Actor-Critic Approach to Multi-Agent Debate. CoRR Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu
2024	A*	`conf`	Achievable Fairness on Your Data With Utility Guarantees. NeurIPS Muhammad Faaiz Taufiq, Jean-Francois Ton, Yang Liu
2024	A*	`conf`	Conformal Counterfactual Inference under Hidden Confounding. KDD Zonghao Chen, Ruocheng Guo, Jean-Francois Ton, Yang Liu
2024	J	`jnl`	Dataset Fairness: Achievable Fairness on Your Data With Utility Guarantees. CoRR Muhammad Faaiz Taufiq, Jean-Francois Ton, Yang Liu
2024	A*	`conf`	Fair Classifiers that Abstain without Harm. ICLR Tongxin Yin, Jean-Francois Ton, Ruocheng Guo, Yuanshun Yao, Mingyan Liu, Yang Liu
2024	J	`jnl`	Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting. CoRR Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu
2024	A*	`conf`	Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation. NeurIPS Xiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, Yang Liu
2024	J	`jnl`	Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation. CoRR Xiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, Yang Liu
2024	J	`jnl`	Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives. CoRR Hao Sun, Yunyi Shen, Jean-Francois Ton
2024	J	`jnl`	Understanding Chain-of-Thought in LLMs through Information Theory. CoRR Jean-Francois Ton, Muhammad Faaiz Taufiq, Yang Liu
2023	J	`jnl`	Deep Concept Removal. CoRR Yegor Klochkov, Jean-Francois Ton, Ruocheng Guo, Yang Liu, Hang Li
2023	A*	`conf`	Invariant Learning via Probability of Sufficient and Necessary Causes. NeurIPS Mengyue Yang, Yonggang Zhang, Zhen Fang, Yali Du, Furui Liu, Jean-Francois Ton, Jianhong Wang, Jun Wang
2023	J	`jnl`	Invariant Learning via Probability of Sufficient and Necessary Causes. CoRR Mengyue Yang, Zhen Fang, Yonggang Zhang, Yali Du, Furui Liu, Jean-Francois Ton, Jun Wang
2023	A*	`conf`	Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits. NeurIPS Muhammad Faaiz Taufiq, Arnaud Doucet, Rob Cornish, Jean-Francois Ton
2023	J	`jnl`	Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits. CoRR Muhammad Faaiz Taufiq, Arnaud Doucet, Rob Cornish, Jean-Francois Ton
2023	A*	`conf`	Rectifying Unfairness in Recommendation Feedback Loop. SIGIR Mengyue Yang, Jun Wang, Jean-Francois Ton
2023	J	`jnl`	Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment. CoRR Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo, Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, Hang Li
2022	A*	`conf`	Conformal Off-Policy Prediction in Contextual Bandits. NeurIPS Muhammad Faaiz Taufiq, Jean-Francois Ton, Rob Cornish, Yee Whye Teh, Arnaud Doucet
2022	J	`jnl`	Conformal Off-Policy Prediction in Contextual Bandits. CoRR Muhammad Faaiz Taufiq, Jean-Francois Ton, Robert Cornish, Yee Whye Teh, Arnaud Doucet
2022	A	`conf`	Grassmann Stein Variational Gradient Descent. AISTATS Xing Liu, Harrison Zhu, Jean-Francois Ton, George Wynne, Andrew B. Duncan
2022	—	`conf`	Regularized Training of Nearest Neighbor Language Models. NAACL-HLT (Student Research Workshop) Jean-Francois Ton, Walter Talbott, Shuangfei Zhai, Joshua M. Susskind
2021	A*	`conf`	BayesIMP: Uncertainty Quantification for Causal Data Fusion. NeurIPS Siu Lun Chau, Jean-Francois Ton, Javier González, Yee Whye Teh, Dino Sejdinovic
2021	A	`conf`	Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings. AISTATS Jean-Francois Ton, Lucian Chan, Yee Whye Teh, Dino Sejdinovic
2021	J	`jnl`	Regularized Training of Nearest Neighbor Language Models. CoRR Jean-Francois Ton, Walter Talbott, Shuangfei Zhai, Josh M. Susskind
2021	A*	`conf`	Robust Pruning at Initialization. ICLR Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh
2021	J	`jnl`	Towards a Unified Analysis of Random Fourier Features. J. Mach. Learn. Res. Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic
2020	J	`jnl`	Meta Learning for Causal Direction. CoRR Jean-Francois Ton, Dino Sejdinovic, Kenji Fukumizu
2020	A*	`conf`	MetaFun: Meta-Learning with Iterative Functional Updates. ICML Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh
2020	J	`jnl`	Pruning untrained neural networks: Principles and Analysis. CoRR Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh
2019	A*	`conf`	Automated Model Selection with Bayesian Quadrature. ICML Henry Chai, Jean-Francois Ton, Michael A. Osborne, Roman Garnett
2019	J	`jnl`	Automated Model Selection with Bayesian Quadrature. CoRR Henry Chai, Jean-Francois Ton, Roman Garnett, Michael A. Osborne
2019	J	`jnl`	MetaFun: Meta-Learning with Iterative Functional Updates. CoRR Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh
2019	J	`jnl`	Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings. CoRR Jean-Francois Ton, Lucian Chan, Yee Whye Teh, Dino Sejdinovic
2019	A*	`conf`	Towards a Unified Analysis of Random Fourier Features. ICML Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic
2018	J	`jnl`	A Unified Analysis of Random Fourier Features. CoRR Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic