Jekyll2026-04-06T17:49:25+00:00https://proceedings.mlr.press/v330/feed.xmlProceedings of Machine Learning ResearchProceedings of The 4th Conference on Lifelong Learning Agents
Held in University of Pennsylvania, Philadelphia, PA, USA on 11-14 August 2025
Published as Volume 330 by the Proceedings of Machine Learning Research on 06 April 2026.
Volume Edited by:
Sarath Chandar
Razvan Pascanu
Eric Eaton
Bing Liu
Rupam Mahmood
Amal Rannen-Triki
Series Editors:
Neil D. Lawrence
PMLRRevisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/abbes26a[{"given"=>"Istabrak", "family"=>"Abbes"}, {"given"=>"Gopeshh", "family"=>"Subbaraj"}, {"given"=>"Matthew", "family"=>"Riemer"}, {"given"=>"Nizar", "family"=>"Islah"}, {"given"=>"Tsuguchika", "family"=>"Tabaru"}, {"given"=>"Hiroaki", "family"=>"Kingetsu"}, {"given"=>"Sarath", "family"=>"Chandar"}, {"given"=>"Irina", "family"=>"Rish"}]Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/chen26a[{"given"=>"Annie S", "family"=>"Chen"}, {"given"=>"Govind", "family"=>"Chada"}, {"given"=>"Laura", "family"=>"Smith"}, {"given"=>"Archit", "family"=>"Sharma"}, {"given"=>"Zipeng", "family"=>"Fu"}, {"given"=>"Sergey", "family"=>"Levine"}, {"given"=>"Chelsea", "family"=>"Finn"}]CLA: Latent Alignment for Online Continual Self-Supervised Learning2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/cignoni26a[{"given"=>"Giacomo", "family"=>"Cignoni"}, {"given"=>"Andrea", "family"=>"Cossu"}, {"given"=>"Alexandra", "family"=>"Gomez-Villa"}, {"given"=>"Joost van de", "family"=>"Weijer"}, {"given"=>"Antonio", "family"=>"Carta"}]On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/dong26a[{"given"=>"Zhiyi", "family"=>"Dong"}, {"given"=>"Zixuan", "family"=>"Liu"}, {"given"=>"Yongyi", "family"=>"Mao"}]Learning Without Time-Based Embodiment Resets in Soft-Actor Critic2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/farrahi26a[{"given"=>"Homayoon", "family"=>"Farrahi"}, {"given"=>"A. Rupam", "family"=>"Mahmood"}]Data-dependent and Oracle Bounds on Forgetting in Continual Learning2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/friedman26a[{"given"=>"Lior", "family"=>"Friedman"}, {"given"=>"Ron", "family"=>"Meir"}]Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/goswami26a[{"given"=>"Dipam", "family"=>"Goswami"}, {"given"=>"Liying", "family"=>"Wang"}, {"given"=>"Bartłomiej", "family"=>"Twardowski"}, {"given"=>"Joost van de", "family"=>"Weijer"}]A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/harun26a[{"given"=>"Md Yousuf", "family"=>"Harun"}, {"given"=>"Christopher", "family"=>"Kanan"}]Reinitializing weights vs units for maintaining plasticity in neural networks2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/hernandez-garcia26a[{"given"=>"J. Fernando", "family"=>"Hernandez-Garcia"}, {"given"=>"Shibhansh", "family"=>"Dohare"}, {"given"=>"Jun", "family"=>"Luo"}, {"given"=>"Richard S.", "family"=>"Sutton"}]Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion2026-04-06T00:00:00+00:002026-04-06T00:00:00+00:00https://proceedings.mlr.press/v330/jaziri26a[{"given"=>"Achref", "family"=>"Jaziri"}, {"given"=>"Étienne", "family"=>"Künzel"}, {"given"=>"Visvanathan", "family"=>"Ramesh"}]