NeurIPS 2023 accepted papers on Continual learning
32 of the 3,584 papers accepted at NeurIPS 2023 (0.9%) are on Continual learning, compared with 1.2% at NeurIPS 2022. They fall into 4 topics.
See NeurIPS 2023 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 · 17 papers
- Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models (18 citations)
- NPCL: Neural Processes for Uncertainty-Aware Continual Learning (3 citations)
- Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation (3 citations)
- Prompt-augmented Temporal Point Process for Streaming Event Sequence (3 citations)
- COOM: A Game Benchmark for Continual Reinforcement Learning (2 citations)
- On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm (2 citations)
- CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation (1 citation)
- Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork (1 citation)
- Recasting Continual Learning as Sequence Modeling (1 citation)
- Rewiring Neurons in Non-Stationary Environments (1 citation)
- An Efficient Dataset Condensation Plugin and Its Application to Continual Learning
- CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence
and 5 more in the interactive map.
Class-incremental · 6 papers
- Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration (32 citations)
- FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning (23 citations)
- A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks (9 citations)
- Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation (6 citations)
- Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments (5 citations)
- Loss Decoupling for Task-Agnostic Continual Learning (3 citations)
Continual fine-tuning of LLMs · 6 papers
- Towards Unbounded Machine Unlearning (28 citations)
- RanPAC: Random Projections and Pre-trained Models for Continual Learning (23 citations)
- Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing (9 citations)
- Static and Sequential Malicious Attacks in the Context of Selective Forgetting (4 citations)
- Improving Language Plasticity via Pretraining with Active Forgetting (2 citations)
- Learning to Modulate pre-trained Models in RL (1 citation)
Domain and prompt-based · 3 papers
- Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (19 citations)
- A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm (10 citations)
- RDumb: A simple approach that questions our progress in continual test-time adaptation (3 citations)