ECCV 2026 accepted papers on Continual learning
29 of the 2,834 papers accepted at ECCV 2026 (1.0%) are on Continual learning, compared with 2.0% at ECCV 2024. They fall into 4 topics.
See ECCV 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
Continual fine-tuning of LLMs · 12 papers
- How to Teach Large Multimodal Models New Skills (8 citations)
- Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection (6 citations)
- Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning (6 citations)
- LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning (3 citations)
- Shared LoRA Subspaces for almost Strict Continual Learning (3 citations)
- Beyond Disjoint Tasks: Towards More Natural Continual Learning for Vision-Language Models
- COLA: Continual Orthogonal Low-Rank Adaptation for Class-Incremental Learning
- D-VLAM: Differential Vision and Language Mixing for Rehearsal Free Continual Learning
- Interference-Aware Continual Vision–Language Learning via Instance-Level Expert Routing
- SCoT: Similarity-guided Conflict-aware Task Consolidation for Continual VQA
- VD-LoRA: Adaptive Reuse of Low-Rank Directions for Continual Learning
- SiGMA: Sign-Guided Merging and Adaptation framework for Multimodal Continual Instruction Tuning
Class-incremental · 9 papers
- Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions (3 citations)
- Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection (2 citations)
- Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection (2 citations)
- Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning (1 citation)
- REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling (1 citation)
- DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery
- Multi-Anchor Distillation with Text-Guided Analytic Classifier for Continual Learning
- Virtual Category-Guided Continual Generalized Category Discovery
- Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
Online and replay-based · 5 papers
- Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces (2 citations)
- Learning Probabilistic Prompt for Continual Learning
- Mitigate Modality-Asymmetric Forgetting via Stabilizing Visual Representations in CLIP-Based Class-Incremental Learning
- Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
- On the Plasticity Collapse in Continual Machine Unlearning
