NeurIPS 2025 accepted papers on Continual learning
55 of the 5,812 papers accepted at NeurIPS 2025 (0.9%) are on Continual learning, compared with 1.1% at NeurIPS 2024. They fall into 4 topics.
See NeurIPS 2025 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
- DOTA: Distributional Test-time Adaptation of Vision-Language Models (3 citations)
- Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning (3 citations)
- Continuous Subspace Optimization for Continual Learning (2 citations)
- Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging (2 citations)
- MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging (2 citations)
- Continual Multimodal Contrastive Learning (1 citation)
- Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models (1 citation)
- Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
- Continual Optimization with Symmetry Teleportation for Multi-Task Learning
- DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces
- Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams
- GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
and 10 more in the interactive map.
Online and replay-based · 20 papers
- Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning (1 citation)
- Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings (1 citation)
- Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion (1 citation)
- Resource-Constrained Federated Continual Learning: What Does Matter? (1 citation)
- Temporal-Difference Variational Continual Learning (1 citation)
- A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
- Auto-Compressing Networks
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
- Compact Memory for Continual Logistic Regression
- Continual Knowledge Adaptation for Reinforcement Learning
- Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
- Gradient-Guided Epsilon Constraint Method for Online Continual Learning
and 8 more in the interactive map.
Class-incremental · 7 papers
- AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection (2 citations)
- Class-wise Balancing Data Replay for Federated Class-Incremental Learning (2 citations)
- Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation
- Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
- Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
- Confusion-Driven Self-Supervised Progressively Weighted Ensemble Learning for Non-Exemplar Class Incremental Learning
- Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning
Domain and prompt-based · 6 papers
- ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains (2 citations)
- C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning (1 citation)
- GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation (1 citation)
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning (1 citation)
- Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
- Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning