NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
889 results for “area:"transfer learning, meta learning, and lifelong learning"” in ICLR 2027. 279 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]How Much to Expand, and How to Route: Dynamic-Capacity Mixture-of-Experts for Continual Learning▼4.5k2.67
[PDF]Beyond Representation Drift: Decomposed Relative Geometry Preservation for Continual Vision-Language Learning▼5.8k2.33
[PDF]Vision Pretraining for Time-Series Forecasting Depends on More Than Undirected Grid Topology▼1361.33
[PDF]MADE: A Memory-Augmented Distribution Expansion Approach via Sleep Consolidation for Context-Based Offline Meta-Reinforcement Learning▼5.8k2.33
[PDF]CAMP: Coupled Alignment of Manifold and Prototypes for Exemplar-Free Class-Incremental Learning▼5.8k2.33
[PDF]Reparameterize Before You Extract: Training-Free Spectral Preconditioning for Knowledge Transfer▲1.7k3.33
[PDF]Skip, Adapt, or Route? Certified Deployment of Test-Time Adaptive Rerankers under Limited Labels▼1.2k1.67
[PDF]Reducing Pretrained Representation Degradation in Parameter-Efficient Continual Learning▼5.8k2.33
[PDF]SHIFT: Receiver-Conditioned Prediction-Space Transfer for Low-Data RGB-to-Thermal Adaptation▲143.33
[PDF]ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience▼5.8k2.33
[PDF]Protect What Is at Risk, Distill Where It Responds: On-Policy Distillation for Continual Learning in MLLMs▲5103.00
Withdrawn or desk rejected (279)
[PDF]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33
[PDF]The Normalization Landscape in Continual Learning: Resolving Moving-Average Breakdown and Subspace Interference for Buffer-Free Edge IntelligenceWithdrawn
[PDF]Beyond Online Accuracy: What Persists After Continual Test-Time Adaptation of Multimodal LLMs on Multiple-Choice VQA?Withdrawn1.67
[PDF]Beyond the Observed: Knowledge-Informed Controllable Augmentation for Few-Shot Class-Incremental LearningWithdrawn1.50