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
140 results for “keyword:"catastrophic forgetting"” in ICLR 2027. 36 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Present Action Is Not Persistent Write: Causal Rights of Optimizer History in Replay-Free Continual Learning▼71.25
[PDF]CLoRE: Drift-Controlled Continual Learning of LLMs via Expert Expansion with Reservoir Routing▲9.2k2.67
[PDF]Why Subspace Protection Needs a Fixed Rank and Neuron Recycling in Task-Free Continual Learning▲3952.67
[PDF]Static Gradient Attribution Underperforms a Density-Matched Random Mask Within LoRA’s B-Matrix▼1.2k1.67
[PDF]Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment▼4.5k2.67
[PDF]NLMR: Neuron-Level Locate-then-Merge for Multilingual Reasoning in English-Centric LLMs▼4.3k2.00
[PDF]Specialist Drift: Continual RL for Capability-Preserving Foundation Model Post-Training▲6.1k2.00
[PDF]Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss▼4.5k2.67
[PDF]Auditing Permanence: Exact Write Accounting and a Matched-Volume Control for Optimizer-State Gates▼4.3k2.00
[PDF]Reward-Proportional Routing of LoRA Experts for Continual Learning in Large Language Models▼1.2k1.67
[PDF]VidMem: Measuring Memorization Capacity and Knowledge Displacement in Video-Language Models▼5.9k2.50
[PDF]Adapting to Rare Regimes without Forgetting: Layered Neuron Plasticity for Spatiotemporal Forecasting▼1.2k1.67
[PDF]Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph–Text Models▲5.4k3.00
[PDF]ProtoCIL: Class-Incremental Learning for Protein Representations with Adaptive Prototypes▼4.5k2.67
[PDF]Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel in Continual Learning▼4.3k2.00
Withdrawn or desk rejected (36)
[PDF]"The Whole Is Greater Than the Sum of Its Parts”: A Multi-Teacher CoT Distillation FrameworkDesk rejected
[PDF]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33
[PDF]MapSelect: Mapping Preservation and Adapter Selection for Continual Multimodal Instruction TuningWithdrawn2.00
[PDF]Multi-Label Class-Incremental Learning for Ophthalmic Diagnosis over a Recurring PopulationWithdrawn1.67
[PDF]Micro-Agent: Mitigating Catastrophic Forgetting in Microscopic Spatial Prediction and Semantic QA through Two-Stage Adaptive OptimizationWithdrawn1.00
[PDF]Beyond Experience Replay: Learning Structural Memory for Online Continual LearningWithdrawn1.33