At least 20 papers with a connection to WASP have been accepted to ICML 2026, highlighting the program’s strong contribution to international research in machine learning.

The accepted papers involve researchers across the WASP community and cover a broad range of topics, including probabilistic methods, robust machine learning, reinforcement learning, diffusion models, computer vision, molecular generation and responsible AI.

ICML is one of the major international conferences in machine learning. This year, 6,352 papers were accepted out of 23,918 submissions that entered the review process, corresponding to an acceptance rate of 26.6 percent. The conference is held in Seoul, South Korea, July 6-11.

Have we missed anyone? Please send and email to wasp.newsletter@partner.liu.se and we’ll be happy to update the list below.

WASP-related papers accepted to ICML 2026

• S. Olsson, B. Pavesi. Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operators, ICML 2026.
• T. Papamarkou, P. Alquier, M. Bauer, W. Buntine, A. Davison, G. K. Dziugaite, M. Filippone, A. YK Foong, V. Fortuin, D. Fouskakis, E. Hüllermeier, T. Karaletsos, M. E. Khan, N. Kotelevskii, S. Lahlou, Y. Li, F. Liu, C. Lyle, T. Möllenhoff, K. Palla, M. Panov, Y. Sale, K. Schweighofer, A. Shelmanov, S. Swaroop, M. Trapp, W. Waegeman, A. G. Wilson, A. Zaytsev. Position: Agentic AI orchestration should be Bayes-consistent, ICML 2026.
• S. Ek, D. Zachariah. Learning Treatment Allocations with Risk Control Under Partial Identifiability, ICML 2026.
• J. Andersson, Z. Zhao. Diffusion differentiable resampling, ICML 2026.
• L. Ju, M. Nautiyal, A. Hellander, E. Vats, P. Singh. Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching, ICML 2026.
• R. Tedoldi, O. Engkvist, P. Bryant, H. Azizpour, J. P. Janet, A. Tibo. FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble, ICML 2026.
• A. Mehrpanah, M. Gamba, H. Azizpour. Improving Adversarial Robustness of Attribution via Implicit Regularization, ICML 2026.
• S. Ericksson, M. Johanson. Clipping makes distributed and federated asynchronous SGD robust to stragglers, ICML 2026.
• V. Shahverdi, G. L. Marchetti, G. Bökman, K. Kohn. Identifiable Equivariant Networks are Layerwise Equivariant, ICML 2026.
• Z. Li, H. Hu, S. H. Lim, X. Li, F. Gao, E. Diao, Z. Ding, M. Vazirgiannis, H. Boström. A Kinetic-Energy Perspective of Flow Matching, ICML 2026. [Spotlight, Top 2.2%]
• M. Selim, C. Cipriani, K. H. Johansson. Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning, ICML 2026.
• F. Kapl, A.M. Karimi Mamaghan, M. Seitzer, K. H. Johansson, C. Marr, S. Bauer, A. Dittadi. Are Object-Centric Representations Better At Compositional Generalization?, ICML 2026.
• Z. Wang, R. De Santi, X. Mo, M. M. Zavlanos, A. Krause, K. H. Johansson. Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning, ICML 2026.
• K. Friedl, N. Jaquier, A. Liao, D. Kragic. Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach, ICML 2026.
• J. Wikman, A. Proutiere, D. Broman. Adaptive Reinforcement Learning for Unobservable Randaom Delays, ICML 2026.
• M. Andrae, E. Larsson, S. Takao, T. Landelius, F. Lindsten. DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants, ICML 2026.
• A. Millard, F. Lindsten, Z. Zhao. Particle-Guided Diffusion Models for Partial Differential Equations, ICML 2026.
• S. N. Wilson, G. F. Guðmundsdóttir, A. Millard, R. Selvan, S. Mair. Position: Stop Preaching and Start Practising Data Frugality for Responsible Development of AI, ICML 2026.
• I. Athanasiadis, A. Karmush, M. Felsberg. Grounding Functional Similarity by Invariance-Aware Model Stitching, ICML 2026.