Major success at ICML 2026 with 13 accepted papers, spotlight recognition, and tutorial
Researchers from our Algorithms, Data, and Artificial Intelligence section have achieved a major research milestone at the 43rd International Conference on Machine Learning (ICML 2026), with 13 accepted papers, one paper selected for Spotlight presentation, and a tutorial.
Widely regarded as one of the world’s top conferences in artificial intelligence and machine learning, ICML brings together leading researchers from academia and industry to present cutting-edge advances in AI, machine learning, statistics, data science, robotics, and related fields.
Among the accepted papers, “Revenue Efficiency of Correlated Equilibria in First Price Auctions” by Anders Bo Ipsen and Stratis Skoulakis was selected for Spotlight presentation — a distinction awarded to a small selection of particularly notable contributions.
The accepted papers span a broad range of topics, including machine learning theory, optimization, explainable AI, time series analysis, quantum algorithms, low-precision training, and AI systems.
The department’s accepted ICML 2026 papers are:
- Revenue Efficiency of Correlated Equilibria in First Price Auctions
Anders Bo Ipsen and Stratis Skoulakis (Spotlight) - The Optimal Sample Complexity of Linear Contracts
Mikael Møller Høgsgaard - RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
Xuan Zhao, Lena Krieger, Zhuo Cao, Arya Bangun, Hanno Scharr, Ira Assent - Unified Time Series Explanations via Semi-Amortized Optimization and Instance-level Multi-Expert Knowledge Distillation
Viet-Hung Tran, Zichi Zhang, Ngoc Phu Doan, Xuan Hoang Nguyen, Phi Hung Nguyen, Yimeng An, Peixin Li, Hans Vandierendonck, Ira Assent, Son Thai Mai - Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
Yi Feng, Weiming Ou, Xiao Wang - Terminal Dimension Reduction for Time Series with Applications
Alexander Munteanu, Matteo Russo, David Saulpic, Chris Schwiegelshohn - Approximation Preserving Coresets
Milind Prabhu, Chris Schwiegelshohn, Sudarshan Shyam - M+Adam: Low-Precision Training via Mantissa–Exponent Optimization
Xiaoyuan Liang, Sebastian Loeschcke, Mads Toftrup, Anima Anandkumar - The benefits of full data shuffle, now with optimal I/O cost: k-wise independence and matrix transposition to the rescue
Peyman Afshani, Rezaul Chowdhury, Mayank Goswami, Jens Kristian Refsgaard Schou, Francesco Silvestri, Mariafiore Tognon - An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
Allan Grønlund, Kasper Green Larsen - Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets
Kasper Green Larsen, Natascha Schalburg - A Fine-Grained Understanding of Uniform Convergence for Halfspaces
Aryeh Kontorovich, Kasper Green Larsen - The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity
Mikael Møller Høgsgaard, Kasper Green Larsen, Liang-Yu Zou
In addition, Akhil Arora, together with Nouha Dziri, has been selected to present the ICML 2026 tutorial “Adaptive Reasoning in LLMs: From Post-Training to Test-Time Learning.” Tutorials are highly competitive and play a central role in shaping discussions and emerging directions within the machine learning community.
This year’s conference takes place in Seoul, South Korea, from July 6–11, 2026. Read more about ICML 2026 at https://icml.cc/