ICLR 2026 accepted papers on Continual learning
58 of the 5,358 papers accepted at ICLR 2026 (1.1%) are on Continual learning, compared with 1.1% at ICLR 2025. They fall into 4 topics.
See ICLR 2026 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
Continual fine-tuning of LLMs · 22 papers
- Remaining-data-free Machine Unlearning by Suppressing Sample Contribution (1 citation)
- Attention Smoothing Is All You Need For Unlearning
- Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
- KeepLoRA: Continual Learning with Residual Gradient Adaptation
- LCA: Local Classifier Alignment for Continual Learning
- Machine Unlearning under Retain–Forget Entanglement
- Mapping Post-Training Forgetting in Language Models at Scale
- Merge before Forget: A Single LoRA Continual Learning via Continual Merging
- One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
- PACE: Pretrained Audio Continual Learning
- Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
- Revisiting Weight Regularization for Low-Rank Continual Learning
and 10 more in the interactive map.
Online and replay-based · 21 papers
- Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
- CONCUR: A Framework for Continual Constrained and Unconstrained Routing
- FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity Tradeoff
- FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
- Forget Forgetting: Continual Learning in a World of Abundant Memory
- IDER: IDEMPOTENT EXPERIENCE REPLAY FOR RELIABLE CONTINUAL LEARNING
- Lifelong Embodied Navigation Learning
- Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
- Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning
- Rethinking Continual Learning with Progressive Neural Collapse
- SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
- The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
and 9 more in the interactive map.
Class-incremental · 14 papers
- Consistency-Driven Calibration and Matching for Few-Shot Class Incremental Learning
- Decoupling the Class Label and the Target Concept in Machine Unlearning
- Lifelong Learning with Behavior Consolidation for Vehicle Routing
- SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
- Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning
- Asymmetric Synthetic Data Update for Domain Incremental Dataset Distillation
- Interference-Isolated Elastic Weight Consolidation and Knowledge Calibration for Incremental Object Detection
- Naming to Learn: Class Incremental Learning for Vision-Language Model with Unlabeled Data
- Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning
- PRISM: Progressive Robust Learning for Open-World Continual Category Discovery
- Random Anchors with Low-rank Decorrelated Learning: A Minimalist Pipeline for Class-Incremental Medical Image Classification
- StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning
and 2 more in the interactive map.