ICML 2024 accepted papers on Continual learning
25 of the 2,610 papers accepted at ICML 2024 (1.0%) are on Continual learning, compared with 1.1% at ICML 2023. They fall into 4 topics.
See ICML 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Online and replay-based · 15 papers
- Rethinking Momentum Knowledge Distillation in Online Continual Learning (2 citations)
- Learning to Continually Learn with the Bayesian Principle (1 citation)
- On the Diminishing Returns of Width for Continual Learning (1 citation)
- Understanding Forgetting in Continual Learning with Linear Regression (1 citation)
- An Effective Dynamic Gradient Calibration Method for Continual Learning
- Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
- Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
- Provable Contrastive Continual Learning
- Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
- Self-Composing Policies for Scalable Continual Reinforcement Learning
- Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
- Bayesian Adaptation of Network Depth and Width for Continual Learning
and 3 more in the interactive map.
Continual fine-tuning of LLMs · 4 papers
- Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models (2 citations)
- COPAL: Continual Pruning in Large Language Generative Models
- DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
- What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement