TPAMI 2026 papers on Continual learning
20 of the 880 papers published in TPAMI 2026 (2.3%) are on Continual learning, compared with 2.4% at TPAMI 2025. They fall into 4 topics.
See TPAMI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Online and replay-based · 7 papers
- Incremental Online Learning of Randomized Neural Network With Forward Regularization (9 citations)
- Dual-CBA: Improving Online Continual Learning via Dual Continual Bias Adaptors From a Bi-level Optimization Perspective (4 citations)
- Elastic Multi-Gradient Descent for Parallel Continual Learning (2 citations)
- Co$^{2}$ In : a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration
- Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
- Latency-Aware Adaptive Learning for Nonstationary Data Streams: Coordinating Concept Drift and Delayed Supervision
- Task Relevance-Driven Prompt Expansion for Federated Continual Learning
Continual fine-tuning of LLMs · 6 papers
- Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective (12 citations)
- Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization (9 citations)
- Practical Continual Forgetting for Pre-Trained Vision Models (6 citations)
- Continual Low-Rank Adaptation Via Cumulative Unified Optimization
- InfBA: Interference-Free Bottleneck Adaptation for Continual Learning
- Learning Evolution via Optimization Knowledge Adaptation
Class-incremental · 4 papers
- Quadruplet Augmentation With Attribute and Structure Invariance for Online Continual Learning (1 citation)
- Happy++: Toward Stable and Unified Continual Generalized Category Discovery
- PointPDF V2: A Unified Framework for Continual Open-World 3D Semantic Segmentation
- Mamba-FSCIL: Dynamic Adaptation With Selective State Space Model for Few-Shot Class Incremental Learning
