CoLLAs 2025

37 papers

A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization Md Yousuf Harun, Christopher Kanan

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

Addressing the Devastating Effects of Single-Task Data Poisoning in Exemplar-Free Continual Learning Stanisław Pawlak, Bartłomiej Twardowski, Tomasz Trzcinski, Joost van de Weijer

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning Rafał Surdej, Michał Bortkiewicz, Alex Lewandowski, Mateusz Ostaszewski, Clare Lyle

Benchmarking Mobile Device Control Agents Across Diverse Configurations Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Changyeon Kim, Kimin Lee

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

BOWL: A Deceptively Simple Open World Learner Roshni Ramanna Kamath, Rupert Mitchell, Subarnaduti Paul, Kristian Kersting, Martin Mundt

CLA: Latent Alignment for Online Continual Self-Supervised Learning Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa, Joost van de Weijer, Antonio Carta

CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation Shishir Muralidhara, Didier Stricker, René Schuster

Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning Elia Piccoli, Malio Li, Giacomo Carfi’, Vincenzo Lomonaco, Davide Bacciu

Data-Dependent and Oracle Bounds on Forgetting in Continual Learning Lior Friedman, Ron Meir

Enhancing Plasticity for First Session Adaptation Continual Learning Imad Eddine Marouf, Subhankar Roy, Stéphane Lathuilière, Enzo Tartaglione

Extremely Simple Streaming Forest Haoyin Xu, Jayanta Dey, Sambit Panda, Joshua T Vogelstein

Improving Multimodal Large Language Models Using Continual Learning Shikhar Srivastava, Md Yousuf Harun, Robik Singh Shrestha, Christopher Kanan

Learning Without Time-Based Embodiment Resets in Soft-Actor Critic Homayoon Farrahi, A. Rupam Mahmood

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance Pranshu Malviya, Jerry Huang, Aristide Baratin, Quentin Fournier, Sarath Chandar

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos Yanlai Yang, Mengye Ren

Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion Achref Jaziri, Étienne Künzel, Visvanathan Ramesh

NoProp: Training Neural Networks Without Back-Propagation or Forward-Propagation Qinyu Li, Yee Whye Teh, Razvan Pascanu

On Supernet Transfer Learning for Effective Task Adaptation Prabhant Singh, Joaquin Vanschoren

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective Zhiyi Dong, Zixuan Liu, Yongyi Mao

Prediction-Oriented Subsampling from Data Streams Benedetta Lavinia Mussati, Freddie Bickford Smith, Tom Rainforth, S Roberts

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mo Chen, Sharan Vaswani

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models Dipam Goswami, Liying Wang, Bartłomiej Twardowski, Joost van de Weijer

Reevaluating Meta-Learning Optimization Algorithms Through Contextual Self-Modulation Roussel Desmond Nzoyem, David A.W. Barton, Tom Deakin

Reinitializing Weights vs Units for Maintaining Plasticity in Neural Networks J. Fernando Hernandez-Garcia, Shibhansh Dohare, Jun Luo, Richard S. Sutton

Replay Can Provably Increase Forgetting Yasaman Mahdaviyeh, James Lucas, Mengye Ren, Andreas S. Tolias, Richard Zemel, Toniann Pitassi

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

Retrieval-Augmented Decision Transformer: External Memory for In-Context RL Thomas Schmied, Fabian Paischer, Vihang Prakash Patil, Markus Hofmarcher, Razvan Pascanu, Sepp Hochreiter

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

SECURE: Semantics-Aware Embodied Conversation Under Unawareness for Lifelong Robot Learning Rimvydas Rubavicius, Peter David Fagan, Alex Lascarides, Subramanian Ramamoorthy

Self-Regulated Neurogenesis for Online Data-Incremental Learning Murat Onur Yildirim, Elif Ceren Gok Yildirim, Decebal Constantin Mocanu, Joaquin Vanschoren

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

Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection Riccardo De Monte, Davide Dalle Pezze, Gian Antonio Susto

Using Partition-Tree Weighting and MAML for Continual and Online Learning Anna Koop, Michael Bowling, Michael Bradley Johanson

Warming up for Zeroth-Order Federated Pre-Training with Low Resource Clients Gwen Legate, Irina Rish, Eugene Belilovsky

What Can Grokking Teach Us About Learning Under Non-Stationarity? Clare Lyle, Ghada Sokar, András György, Razvan Pascanu