Table of Contents

• Energy-Based Models for Continual LearningShuang Li, Yilun Du, Gido van de Ven, Igor Mordatch. 1-22 [doi]
• How Does the Task Landscape Affect MAML Performance?Liam Collins, Aryan Mokhtari, Sanjay Shakkottai. 23-59 [doi]
• Continual Learning with Foundation Models: An Empirical Study of Latent ReplayOleksiy Ostapenko, Timothée Lesort, Pau Rodríguez, Md Rifat Arefin, Arthur Douillard, Irina Rish, Laurent Charlin. 60-91 [doi]
• EFL: Elastic Federated Learning on Non-IID DataZichen Ma, Yu Lu, Wenye Li 0001, Shuguang Cui. 92-115 [doi]
• Disentanglement and Generalization Under Correlation ShiftsChristina M. Funke, Paul Vicol, Kuan-Chieh Wang, Matthias Kümmerer, Richard S. Zemel, Matthias Bethge. 116-141 [doi]
• Practical Tradeoffs between Memory, Compute, and Performance in Learned OptimizersLuke Metz, C. Daniel Freeman, James Harrison, Niru Maheswaranathan, Jascha Sohl-Dickstein. 142-164 [doi]
• On Anytime Learning at MacroscaleLucas Caccia, Jing Xu, Myle Ott, Marc'Aurelio Ranzato, Ludovic Denoyer. 165-182 [doi]
• Continual Unsupervised Learning for Optical Flow Estimation with Deep NetworksSimone Marullo, Matteo Tiezzi, Alessandro Betti, Lapo Faggi, Enrico Meloni, Stefano Melacci. 183-200 [doi]
• Continual Learning through Hamilton EquationsAlessandro Betti, Lapo Faggi, Marco Gori, Matteo Tiezzi, Simone Marullo, Enrico Meloni, Stefano Melacci. 201-212 [doi]
• Improving Meta-Learning Generalization with Activation-Based Early-StoppingSimon Guiroy, Christopher Pal, Gonçalo Mordido, Sarath Chandar. 213-230 [doi]
• A Rule-based Shield: Accumulating Safety Rules from Catastrophic Action EffectsShahaf S. Shperberg, Bo Liu 0042, Alessandro Allievi, Peter Stone. 231-242 [doi]
• Continual Learning and Private UnlearningBo Liu, Qiang Liu, Peter Stone. 243-254 [doi]
• Overcoming challenges in leveraging GANs for few-shot data augmentationChristopher Beckham, Issam H. Laradji, Pau Rodríguez, David Vázquez 0001, Derek Nowrouzezahrai, Christopher Pal. 255-280 [doi]
• Increasing Model Generalizability for Unsupervised Visual Domain AdaptationMohammad Rostami. 281-293 [doi]
• Forgetting and Imbalance in Robot Lifelong Learning with Off-policy DataWenxuan Zhou, Steven Bohez, Jan Humplik, Nicolas Heess, Abbas Abdolmaleki, Dushyant Rao, Markus Wulfmeier, Tuomas Haarnoja. 294-309 [doi]
• Streaming Inference for Infinite Non-Stationary ClusteringRylan Schaeffer, Gabrielle Kaili-May Liu, Yilun Du, Scott Linderman, Ila Rani Fiete. 310-326 [doi]
• Inexperienced RL Agents Can't Get It Right: Lower Bounds on Regret at Finite Sample ComplexityMaia Fraser, Vincent Létourneau. 327-334 [doi]
• Continual Learning of Dynamical Systems With Competitive Federated Reservoir ComputingLeonard Bereska, Efstratios Gavves. 335-350 [doi]
• Learning Object-Centered Autotelic Behaviors with Graph Neural NetworksAhmed Akakzia, Olivier Sigaud. 351-365 [doi]
• TAG: Task-based Accumulated Gradients for Lifelong learningPranshu Malviya, Balaraman Ravindran, Sarath Chandar. 366-389 [doi]
• Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning ApproachPrashant Shivaram Bhat, Bahram Zonooz, Elahe Arani. 390-405 [doi]
• Zipfian Environments for Reinforcement LearningStephanie C. Y. Chan, Andrew Kyle Lampinen, Pierre Harvey Richemond, Felix Hill. 406-429 [doi]
• CLActive: Episodic Memories for Rapid Active LearningSri Aurobindo Munagala, Sidhant Subramanian, Shyamgopal Karthik, Ameya Prabhu, Anoop M. Namboodiri. 430-440 [doi]
• Reactive Exploration to Cope With Non-Stationarity in Lifelong Reinforcement LearningChristian Alexander Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang Prakash Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter. 441-469 [doi]
• A Dataset Perspective on Offline Reinforcement LearningKajetan Schweighofer, Marius-Constantin Dinu, Andreas Radler, Markus Hofmarcher, Vihang Prakash Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter. 470-517 [doi]
• Predictive Learning Enables Neural Networks to Learn Complex Working Memory TasksThijs Lambik Van der Plas, Sanjay G. Manohar, Tim P. Vogels. 518-531 [doi]
• Benchmarking Learning Efficiency in Deep Reservoir ComputingHugo Cisneros, Tomás Mikolov, Josef Sivic. 532-547 [doi]
• A Multi-Head Model for Continual Learning via Out-of-Distribution ReplayGyuhak Kim, Bing Liu 0001, Zixuan Ke. 548-563 [doi]
• On the Limitations of Continual Learning for Malware ClassificationMohammad Saidur Rahman 0002, Scott E. Coull, Matthew Wright 0001. 564-582 [doi]
• Inherent Limitations of Multi-Task Fair RepresentationsTosca Lechner, Shai Ben-David. 583-603 [doi]
• What Should I Know? Using Meta-Gradient Descent for Predictive Feature Discovery in a Single Stream of ExperienceAlex Kearney, Anna Koop, Johannes Günther 0002, Patrick M. Pilarski. 604-616 [doi]
• Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural ActivationsAli Abbasi, Parsa Nooralinejad, Vladimir Braverman, Hamed Pirsiavash, Soheil Kolouri. 617-628 [doi]
• Test Sample Accuracy Scales with Training Sample Density in Neural NetworksXu Ji, Razvan Pascanu, R. Devon Hjelm, Balaji Lakshminarayanan, Andrea Vedaldi. 629-646 [doi]
• A Theory for Knowledge Transfer in Continual LearningDiana Benavides Prado, Patricia Riddle. 647-660 [doi]
• Simulation-Acquired Latent Action Spaces for Dynamics GeneralizationNicholas Corrado, Yuxiao Qu, Josiah P. Hanna. 661-682 [doi]
• Self-Activating Neural Ensembles for Continual Reinforcement LearningSam Powers, Eliot Xing, Abhinav Gupta 0001. 683-704 [doi]
• CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning AgentsSam Powers, Eliot Xing, Eric Kolve, Roozbeh Mottaghi, Abhinav Gupta 0001. 705-743 [doi]
• Online Continual Learning for Embedded DevicesTyler L. Hayes, Christopher Kanan. 744-766 [doi]
• Heat-RL: Online Model Selection for Streaming Time-Series Anomaly DetectionYujing Wang, Luoxing Xiong, Mingliang Zhang, Hui Xue 0004, Qi Chen, Yaming Yang 0001, Yunhai Tong, Congrui Huang, Bixiong Xu. 767-777 [doi]
• Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine LearningPhung Lai, Han Hu, Hai Phan, Ruoming Jin, My T. Thai, An M. Chen. 778-797 [doi]
• Neural Distillation as a State Representation Bottleneck in Reinforcement LearningValentin Guillet, Dennis George Wilson, Emmanuel Rachelson. 798-818 [doi]
• How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of InterpolationEkdeep Singh Lubana, Puja Trivedi, Danai Koutra, Robert P. Dick. 819-837 [doi]
• Lifelong Robotic Reinforcement Learning by Retaining ExperiencesAnnie Xie, Chelsea Finn. 838-855 [doi]
• Hierarchical Kickstarting for Skill Transfer in Reinforcement LearningMichael Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim Rocktäschel. 856-874 [doi]
• Open Set Recognition Via Augmentation-Based Similarity LearningSepideh Esmaeilpour, Lei Shu 0004, Bing Liu 0001. 875-885 [doi]
• Meta-Gradients in Non-Stationary EnvironmentsJelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh 0001. 886-901 [doi]
• MO2: Model-Based Offline OptionsSasha Salter, Markus Wulfmeier, Dhruva Tirumala, Nicolas Heess, Martin A. Riedmiller, Raia Hadsell, Dushyant Rao. 902-919 [doi]
• SYNERgy between SYNaptic Consolidation and Experience Replay for General Continual LearningFahad Sarfraz, Elahe Arani, Bahram Zonooz. 920-936 [doi]
• Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature SharingNareshKumar Gurulingan, Elahe Arani, Bahram Zonooz. 937-951 [doi]
• Differencing based Self-supervised pretraining for Scene Change DetectionVijaya Raghavan T. Ramkumar, Elahe Arani, Bahram Zonooz. 952-965 [doi]
• Optimal Transport meets Noisy Label Robust Loss and MixUp Regularization for Domain AdaptationKilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas. 966-981 [doi]
• CompoSuite: A Compositional Reinforcement Learning BenchmarkJorge A. Mendez, Marcel Hussing, Meghna Gummadi, Eric Eaton. 982-1003 [doi]
• Continual Novelty DetectionRahaf Aljundi, Daniel Olmeda Reino, Nikolay Chumerin, Richard E. Turner. 1004-1025 [doi]
• InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awarenessShruthi Gowda, Bahram Zonooz, Elahe Arani. 1026-1042 [doi]
• Few-Shot Learning by Dimensionality Reduction in Gradient SpaceMartin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner. 1043-1064 [doi]
• SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class BoundariesMeghna Gummadi, David Kent 0001, Jorge A. Mendez, Eric Eaton. 1065-1085 [doi]
• Trustworthiness Evaluation and Trust-Aware Design of CNN ArchitecturesMingxi Cheng, Tingyang Sun, Shahin Nazarian, Paul Bogdan. 1086-1102 [doi]
• Adapting Pre-trained Language Models to Low-Resource Text Simplification: The Path MattersCristina Garbacea, Qiaozhu Mei. 1103-1119 [doi]
• Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2Zachary Alan Daniels, Aswin Raghavan, Jesse Hostetler, Abrar Rahman, Indranil Sur, Michael Piacentino, Ajay Divakaran, Roberto Corizzo, Kamil Faber, Nathalie Japkowicz, Michael Baron, James Seale Smith, Sahana Pramod Joshi, Zsolt Kira, Cameron Ethan Taylor, Mustafa Burak Gurbuz, Constantine Dovrolis, Tyler L. Hayes, Christopher Kanan, Jhair Gallardo. 1120-1145 [doi]
• Improved Policy Optimization for Online Imitation LearningJonathan Wilder Lavington, Sharan Vaswani, Mark Schmidt 0001. 1146-1173 [doi]
• Learning Skills Diverse in Value-Relevant FeaturesMatthew J. A. Smith, Jelena Luketina, Kristian Hartikainen, Maximilian Igl, Shimon Whiteson. 1174-1194 [doi]
• Consistency is the Key to Further Mitigating Catastrophic Forgetting in Continual LearningPrashant Shivaram Bhat, Bahram Zonooz, Elahe Arani. 1195-1212 [doi]
• Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity ResolutionGeorgios Tziafas, Lambert Schomaker, S. Hamidreza Kasaei. 1213-1230 [doi]
• Probing Transfer in Deep Reinforcement Learning without Task EngineeringAndrei Alex Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell. 1231-1254 [doi]