AAAI 2026 accepted papers on Continual learning
58 of the 4,417 papers accepted at AAAI 2026 (1.3%) are on Continual learning, compared with 1.4% at AAAI 2025. They fall into 4 topics.
See AAAI 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
Class-incremental · 20 papers
- YOLO-IOD: Towards Real Time Incremental Object Detection (4 citations)
- BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning (2 citations)
- Decoupling Continual Semantic Segmentation (1 citation)
- GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery (1 citation)
- Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection
- CiNuSeg: Class Incremental Nuclei Segmentation via Anchor-driven Consistency Learning with Dual Region Regularization
- Class Incremental Medical Image Segmentation via Prototype-Guided Calibration and Dual-Aligned Distillation
- Continual Out-of-Distribution Detection with Analytic Neural Collapse
- DiAPR: Dimensionally-Allocated Prototype Refinement for Non-Exemplar Class Incremental Learning
- Expandable and Differentiable Dual Memories with Orthogonal Regularization for Exemplar-free Continual Learning
- Forget What Has Seen: Selective Concept Unlearning in Segmentation Foundation Models
- Gene Incremental Learning for Single-Cell Transcriptomics
and 8 more in the interactive map.
Online and replay-based · 18 papers
- HiCL: Hippocampal-Inspired Continual Learning (2 citations)
- Catastrophic Forgetting in Kolmogorov-Arnold Networks (1 citation)
- Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory (1 citation)
- HLML-SNN：Fast Continual Learning in Spiking Neural Networks Achieved via Hebbian Learning-Driven Meta-Learning (1 citation)
- Unifying Locality of KANs and Feature Drift Compensation Projection for Data-Free Replay Based Continual Face Forgery Detection (1 citation)
- Attention Retention for Continual Learning with Vision Transformers
- Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning
- CIP-Net: Continual Interpretable Prototype-based Network
- ConSurv: Multimodal Continual Learning for Survival Analysis
- Decomposing Prompts, Composing Actions: A Multi-Granularity Prompting Approach for Incremental Action Learning
- Forget Less by Learning from Parents Through Hierarchical Relationships
- Grow-on-Demand: Sparse and Adaptive Expert Expansion for Continual Instruction Tuning
and 6 more in the interactive map.
Continual fine-tuning of LLMs · 17 papers
- Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learning (4 citations)
- Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning (2 citations)
- ICM-Fusion: In-Context Meta-Optimized LoRA Fusion for Multi-Task Adaptation (2 citations)
- LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning (2 citations)
- Compensating Distribution Drifts in Continual Learning with Pre-trained Vision Transformers (1 citation)
- Forgetting Knowledge Localization and Isolation for Continual Forgetting of Pre-trained Vision Models (1 citation)
- Adapt Before Continual Learning
- Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA
- DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality Learning
- KSS-MoE: Knowledge Space Synergy Framework in Mixture of Experts for Continual Visual Instruction Tuning
- Learning Adaptive and Expandable Mixture Model for Continual Learning
- MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge Through Group Direct Preference Optimization
and 5 more in the interactive map.
Domain and prompt-based · 3 papers
- Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation (1 citation)
- Unified Representation Causal Prompt Distillation for Re-Inference-Free Lifelong Person Re-Identification
- Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation