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453 results for “keyword:"continual learning"” in ICLR 2027. 116 withdrawn or desk rejected listed apart.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]When Preservation Becomes Stale: Continual Functional Refactoring for Fixed-Capacity CLIP Continual Learning▼5.8k2.33
[PDF]PLAN AROUND CHANGES, LEARN FROM VIOLATIONS: PERSISTENT TASK STATE FOR LONG-HORIZON VLA AGENTS▼1361.33
[PDF]Data Selection for Continual Learning: A Theoretical Analysis of Sample Scoring under Task Similarity▼5.8k2.33
[PDF]Loss of Plasticity and Its Recovery via Replay-Driven Compression in a Spiking Model of Hippocampal CA3▼4.3k2.00
[PDF]Scaling Gradient Projection for Continual Learning Over Long Task Sequences via Spectral Consolidation▲5103.00
[PDF]Compile the Catalog, Not the Task: ToolGraph as a Tool-Use Agent Harness that Updates, Scales, and Transfers▲6.1k2.00
[PDF]Forgotten or Inaccessible? Restoration Savings Reveal What Language Models Retain After Fine-Tuning▼4.3k2.00
[PDF]On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification▼4.5k2.67
[PDF]Learning Style, Forgetting Semantics: A case study of SFT and RFT on Classification Tasks▲5.4k3.00
[PDF]Adaptive Distillation via Online Drift Projection for Exemplar-Free Class-Incremental Learning▲3972.67
[PDF]Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy▼1.2k1.67
[PDF]One Graph, Every Node, Hidden Task: HIDE, a Protocol for Graph Class-Incremental Learning▲3.0k2.50
[PDF]On the Stability of Growth in Structural Plasticity: Forward-Active yet Backward-Starved▼4.3k2.00
[PDF]Test-Time Training for Pretrained LLMs: An Empirical Study of Limited Fast-Weight Utilization▲3972.67
[PDF]Retention is Leakage: Forgetting Does Not Confer Privacy in Federated Continual Learning▲13k2.33
[PDF]Neural Succession: A Mesoscopic Theory of Invasion, Coexistence, and Stabilization in Continual Learning▼1.2k1.67
Withdrawn or desk rejected (116)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