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
453 results for “keyword:"continual learning"” in ICLR 2027. 116 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ThoughtVLA: Evolving Thought Trajectories for Continual Vision-Language-Action Adaptation▼5.8k2.33
[PDF]MoCE: Mixture of Communitified Experts for Continual Vision-Language Learning under Task-Complexity Flux▲3.0k2.33
[PDF]Learning from the Past: Experience Replay Strengthens Joint-Embedding Predictive Learning in Language Models▼5.8k2.33
[PDF]PAI: Plasticity-Anchored Initialization for Improved Stability-Plasticity Trade-offs in Continual Learning▼1611.50
[PDF]UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation▼4.5k2.67
[PDF]Adapting to Rare Regimes without Forgetting: Layered Neuron Plasticity for Spatiotemporal Forecasting▼1.2k1.67
[PDF]Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning▼4.5k2.67
[PDF]When Learned Options Become Infrastructure: Promotion-Induced Maintenance in Control Lifecycles▲11.00
[PDF]The Price of Not Forgetting: A Covering-Based Memory-Error Analysis for Continual Time-Series Forecasting under Regime Drift▼1361.33
[PDF]Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph–Text Models▲5.4k3.00
[PDF]CIRCE: Counterfactually Informed Reliable Component Evidence for Continual Phrase-to-Patch Alignment▲3952.67
[PDF]Neural Consolidation Process: Selective Tagging and Validated Capture for Continual Learning▼4.5k2.67
[PDF]Decoupled in Time, Aligned in Space: Geometric Alignment for Temporally Heterogeneous Federated Continual Learning▲3952.67
[PDF]When New Experiments Arrive: An Evidence-adjudicated Self-correction Framework for Virtual Cells▲3952.67
[PDF]Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel in Continual Learning▼4.3k2.00
[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]CAMP: Coupled Alignment of Manifold and Prototypes for Exemplar-Free Class-Incremental Learning▼5.8k2.33
[PDF]Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?▼4.3k2.00
Withdrawn or desk rejected (116)
[PDF]The Normalization Landscape in Continual Learning: Resolving Moving-Average Breakdown and Subspace Interference for Buffer-Free Edge IntelligenceWithdrawn
[PDF]Generalized Residual Closure: General Learning Dynamics for Stability–Plasticity CompatibilityWithdrawn2.00