Enhancing Plasticity for First Session Adaptation Continual Learning

Imad Eddine Marouf, Subhankar Roy, Stéphane Lathuilière, Enzo Tartaglione; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:1-14

[abs][Download PDF]

Replay can provably increase forgetting

Yasaman Mahdaviyeh, James Lucas, Mengye Ren, Andreas S. Tolias, Richard Zemel, Toniann Pitassi; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:15-42

[abs][Download PDF]

Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion

Achref Jaziri, Étienne Künzel, Visvanathan Ramesh; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:43-63

[abs][Download PDF]

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning

Rafał Surdej, Michał Bortkiewicz, Alex Lewandowski, Mateusz Ostaszewski, Clare Lyle; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:64-88

[abs][Download PDF]

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective

Zhiyi Dong, Zixuan Liu, Yongyi Mao; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:89-111

[abs][Download PDF]

Learning Without Time-Based Embodiment Resets in Soft-Actor Critic

Homayoon Farrahi, A. Rupam Mahmood; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:112-135

[abs][Download PDF]

Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning

Elia Piccoli, Malio Li, Giacomo Carfi’, Vincenzo Lomonaco, Davide Bacciu; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:136-161

[abs][Download PDF]

Addressing the Devastating Effects of Single-Task Data Poisoning in Exemplar-free Continual Learning

Stanisław Pawlak, Bartłomiej Twardowski, Tomasz Trzcinski, Joost van de Weijer; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:162-181

[abs][Download PDF]

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos

Yanlai Yang, Mengye Ren; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:182-203

[abs][Download PDF]

Statistical Bias Leads to Overestimated OOD Generalization in Algorithmic Tasks for Seq2Seq Transformer Models

John Kirk; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:204-221

[abs][Download PDF]

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance

Pranshu Malviya, Jerry Huang, Aristide Baratin, Quentin Fournier, Sarath Chandar; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:222-244

[abs][Download PDF]

Extremely Simple Streaming Forest

Haoyin Xu, Jayanta Dey, Sambit Panda, Joshua T Vogelstein; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:245-260

[abs][Download PDF]

Benchmarking Mobile Device Control Agents across Diverse Configurations

Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Changyeon Kim, Kimin Lee; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:261-306

[abs][Download PDF]

Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment

Annie S Chen, Govind Chada, Laura Smith, Archit Sharma, Zipeng Fu, Sergey Levine, Chelsea Finn; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:307-323

[abs][Download PDF]

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models

Dipam Goswami, Liying Wang, Bartłomiej Twardowski, Joost van de Weijer; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:324-340

[abs][Download PDF]

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients

Gwen Legate, Irina Rish, Eugene Belilovsky; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:341-357

[abs][Download PDF]

BOWL: A Deceptively Simple Open World Learner

Roshni Ramanna Kamath, Rupert Mitchell, Subarnaduti Paul, Kristian Kersting, Martin Mundt; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:358-375

[abs][Download PDF]

Retrieval-Augmented Decision Transformer: External Memory for In-context RL

Thomas Schmied, Fabian Paischer, Vihang Prakash Patil, Markus Hofmarcher, Razvan Pascanu, Sepp Hochreiter; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:376-417

[abs][Download PDF]

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection

Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mo Chen, Sharan Vaswani; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:418-444

[abs][Download PDF]

A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization

Md Yousuf Harun, Christopher Kanan; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:445-464

[abs][Download PDF]

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models

Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer, Nizar Islah, Tsuguchika Tabaru, Hiroaki Kingetsu, Sarath Chandar, Irina Rish; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:465-486

[abs][Download PDF]

Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection

Riccardo De Monte, Davide Dalle Pezze, Gian Antonio Susto; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:487-499

[abs][Download PDF]

Reevaluating Meta-Learning Optimization Algorithms Through Contextual Self-Modulation

Roussel Desmond Nzoyem, David A.W. Barton, Tom Deakin; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:500-524

[abs][Download PDF]

NoProp: Training Neural Networks without Back-propagation or Forward-propagation

Qinyu Li, Yee Whye Teh, Razvan Pascanu; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:525-544

[abs][Download PDF]

Replay Consolidation with Label Propagation for Continual Object Detection

Riccardo De Monte, Davide Dalle Pezze, Marina Ceccon, Francesco Pasti, Francesco Paissan, Elisabetta Farella, Gian Antonio Susto, Nicola Bellotto; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:545-564

[abs][Download PDF]

Prediction-Oriented Subsampling from Data Streams

Benedetta Lavinia Mussati, Freddie Bickford Smith, Tom Rainforth, S Roberts; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:565-580

[abs][Download PDF]

On Supernet Transfer Learning for Effective Task Adaptation

Prabhant Singh, Joaquin Vanschoren; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:581-597

[abs][Download PDF]

Using Partition-Tree Weighting and MAML for Continual and Online Learning

Anna Koop, Michael Bowling, Michael Bradley Johanson; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:598-611

[abs][Download PDF]

SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning

Rimvydas Rubavicius, Peter David Fagan, Alex Lascarides, Subramanian Ramamoorthy; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:612-634

[abs][Download PDF]

What can grokking teach us about learning under non-stationarity?

Clare Lyle, Ghada Sokar, András György, Razvan Pascanu; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:635-656

[abs][Download PDF]

Self-Regulated Neurogenesis for Online Data-Incremental Learning

Murat Onur Yildirim, Elif Ceren Gok Yildirim, Decebal Constantin Mocanu, Joaquin Vanschoren; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:657-671

[abs][Download PDF]

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

Vaibhav Singh, Paul Janson, Paria Mehrbod, Adam Ibrahim, Irina Rish, Eugene Belilovsky, Benjamin Thérien; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:672-695

[abs][Download PDF]

CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation

Shishir Muralidhara, Didier Stricker, René Schuster; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:696-712

[abs][Download PDF]

Data-dependent and Oracle Bounds on Forgetting in Continual Learning

Lior Friedman, Ron Meir; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:713-735

[abs][Download PDF]

Improving Multimodal Large Language Models Using Continual Learning

Shikhar Srivastava, Md Yousuf Harun, Robik Singh Shrestha, Christopher Kanan; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:736-755

[abs][Download PDF]

CLA: Latent Alignment for Online Continual Self-Supervised Learning

Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa, Joost van de Weijer, Antonio Carta; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:756-775

[abs][Download PDF]

Reinitializing weights vs units for maintaining plasticity in neural networks

J. Fernando Hernandez-Garcia, Shibhansh Dohare, Jun Luo, Richard S. Sutton; Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:776-806

[abs][Download PDF]