ICLR 2026

Dates: Apr 23 – 27, 2026
Place: Rio de Janeiro, Brazil
Venue: Riocentro Convention and Event Center
Organiser: International Conference on Learning Representations

ICLR 2026, the 14th International Conference on Learning Representations, was held 23-27 April 2026 at Riocentro in Rio de Janeiro, with 9,954 participants from 80 countries. It accepted 5,355 of 19,525 submissions. Outstanding Paper awards went to 'Transformers are Inherently Succinct' and 'LLMs Get Lost In Multi-Turn Conversation'. Talk recordings are on iclr.cc/virtual/2026.

Key facts

Rio de Janeiro edition: ICLR 2026 ran 23-27 April 2026 at Riocentro in Rio de Janeiro, drawing 9,954 participants from 80 countries (7,054 in person).
19,525 submissions: Submissions rose by 7,922 over 2025 to 19,525; 5,355 papers were accepted, a 27.4% acceptance rate.
Two Outstanding Papers: 'Transformers are Inherently Succinct' and 'LLMs Get Lost In Multi-Turn Conversation' won Outstanding Paper, with 'The Polar Express' (Muon optimizer) as Honorable Mention.
Test of Time: DCGAN and DDPG: The Test of Time awards went to two ICLR 2016 papers, DCGAN and DDPG (continuous-control deep RL).
Robotics keynote: Maja Matarić opened the keynotes with a talk on human-centred AI and socially assistive robotics; talks are recorded on the ICLR virtual site.

Keynote speakers

Maja Matarić (University of Southern California; Google DeepMind): The Challenges of Human-Centered AI and Robotics: What We Want, Need, and are Getting From Human-Machine Interaction
Max Welling (University of Amsterdam; CuspAI): From Physics to AI to Materials; A Journey from Foundations to Impact
Percy Liang (Stanford University): Marin: Open Development of Frontier AI
Katie Bouman (California Institute of Technology): Images of the Hidden Universe
Karen Adolph (New York University): Learning while developing: How infants acquire intelligent behavior
Pablo Arbeláez (Universidad de los Andes (CinfonIA)): Artificial Intelligence for Open Science

Workshops

ICLR 2026 Workshop on AI with Recursive Self-Improvement, Sunday April 26: https://recursive-workshop.github.io/
ICLR 2026 Workshop on Lifelong Agents: Learning, Aligning, Evolving, Sunday April 26: https://lifelongagent.github.io/
ICLR 2026 Workshop on Memory for LLM-Based Agentic Systems (MemAgents), Monday April 27: https://sites.google.com/view/memagent-iclr26/
ICLR 2026 the 2nd Workshop on World Models: Understanding, Modelling and Scaling, Monday April 27: https://sites.google.com/view/iclr-2026-workshop-world-model/home

Official links

Website: https://iclr.cc/Conferences/2026
Talk recordings: https://iclr.cc/virtual/2026/index.html