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
558 results for “keyword:"continual"” in ICLR 2027. 154 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reset or Reuse? Understanding How Optimizer Memory Shapes Continual Mixture-of-Experts Learning▼4.3k2.00
[PDF]CORE: Collaborative Orthogonal Residual Experts for Multimodal Continual Instruction Tuning▼1.2k1.67
[PDF]When Better Routing Hides a Worse Prompt Update: Classifier-Conditioned Evaluation in Domain-Incremental Learning▲6.1k2.00
[PDF]Prior to Memory: Bayesian Assignment Projection for Continual Generalized Category Discovery▼5.8k2.33
[PDF]Specialists Learn Faster: Knowledge Organization in Pre-Training Shapes Knowledge Update Efficiency▼4.3k2.00
[PDF]Learning to Recover: Iteratively Internalizing Agent Corrections into VLAs for Robotic Manipulation▼4.5k2.67
[PDF]ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning▲432.75
[PDF]Zero-Drift Expert Pool: Factorized Routing for Stable Pre-Trained-Model Continual Learning▲11.00
[PDF]GeoSpec: Geometry-Guided Expert Specialization for Multimodal Continual Instruction Tuning▼5.8k2.33
[PDF]From Solving Data Tasks to Learning a Data Space: Benchmarking Learning Capabilities of Data Agents▼1.2k3.00
[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]DualMem-Evo: Dual-Memory Evolution for Replay-Free Continual Adaptation of Vision-Language Models▼5.8k2.33
[PDF]ReDraft, Don't Just Distill: Reference-Driven Revision for Continual MLLM Post-Training▼4.3k2.00
[PDF]VidMem: Measuring Memorization Capacity and Knowledge Displacement in Video-Language Models▼5.9k2.50
[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
Withdrawn or desk rejected (154)
[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]HarnessQuotient: Counterexample-Guided Behavioral Quotienting for Self-Evolving Agent HarnessesWithdrawn
[PDF]Generalized Residual Closure: General Learning Dynamics for Stability–Plasticity CompatibilityWithdrawn2.00