ICLR 2026

Datas: 23 – 27 de abr. de 2026
Local: Rio de Janeiro, Brazil
Local do evento: Riocentro Convention and Event Center
Organizador: International Conference on Learning Representations

A ICLR 2026, 14ª International Conference on Learning Representations, foi realizada de 23 a 27 de abril de 2026 no Riocentro, no Rio de Janeiro, com 9.954 participantes de 80 países. Foram aceitas 5.355 de 19.525 submissões. Os prêmios de Outstanding Paper foram para 'Transformers are Inherently Succinct' e 'LLMs Get Lost In Multi-Turn Conversation'. As gravações das palestras estão em iclr.cc/virtual/2026.

Fatos principais

Edição no Rio de Janeiro: A ICLR 2026 ocorreu de 23 a 27 de abril de 2026 no Riocentro, no Rio de Janeiro, e reuniu 9.954 participantes de 80 países (7.054 presencialmente).
19.525 submissões: As submissões aumentaram em 7.922 em relação a 2025, chegando a 19.525; 5.355 artigos foram aceitos, uma taxa de aceitação de 27,4%.
Dois Outstanding Papers: 'Transformers are Inherently Succinct' e 'LLMs Get Lost In Multi-Turn Conversation' venceram o Outstanding Paper, com 'The Polar Express' (otimizador Muon) como Honorable Mention.
Test of Time: DCGAN e DDPG: Os prêmios Test of Time foram para dois artigos da ICLR 2016, DCGAN e DDPG (deep RL para controle contínuo).
Keynote de robótica: Maja Matarić abriu as keynotes com uma palestra sobre IA centrada no ser humano e robótica socialmente assistiva; as palestras estão gravadas no site virtual da ICLR.

Palestrantes principais

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

Links oficiais

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