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
55 results for “keyword:"retention"” in ICLR 2027. 18 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LAB-Sparse: Local Accumulative Boost for Adaptive Semantic-Block Retention in KV Cache▼4.3k2.00
[PDF]RASA: Retention-Aware Stream Adaptation for Online Continual Learning in Large Language Models▲5103.00
[PDF]Not All Forgetting Is Equal: Budgeted Preference Optimization for Retaining Critical Capabilities▲3952.67
[PDF]Curves, Not Points: Structured Curve Approximation for Engagement Dynamics in Short-Form Video and Interactive Live Streaming▼4.3k2.00
[PDF]What Should We Freeze? Guarded Freezing: Connectivity Shapes the Fine-Tuning of Pretrained Models▲6.1k2.00
[PDF]Lipschitz-Constrained Selective State-Space Models with State-Retention and PAC-Bayesian Bounds Against Hidden-State Poisoning▼4.3k2.00
[PDF]Retention is Leakage: Forgetting Does Not Confer Privacy in Federated Continual Learning▲13k2.33
[PDF]GeoLACE: Geometric Layerwise Action-Conditioned Enhancement for Vision-Language-Action Models▼4.5k2.67
[PDF]Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases▼12k1.67
[PDF]How Much Is a Memory Worth? Efficient Credit Assignment for Memory Admission Under Unknown Demand▼5.8k2.33
[PDF]Condition-Specific Weighted Data Sparsification for Compute-Efficient Physical-System Regression▼4.3k2.00
[PDF]MemoryLifeBench: Evaluating Survival-Based and Utility-Ranked Memory Retention in LLM Assistants▼1361.33
[PDF]How Early Does Context Reduction Become Computationally Valuable? Capacity–Value Separation in Long-Context Prefill▼1.2k1.67
[PDF]When Zero Cost Does Not Mean Safe: Response Delay and Policy Delivery in Resource-Constrained Reinforcement Learning▼1.3k1.75
[PDF]Capability Budgeting: Acquiring Mathematical Reasoning While Retaining Capabilities in Multilingual Continual Pretraining▼1.3k1.75
[PDF]Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation▼1.3k1.75
[PDF]ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory▼1361.33
[PDF]Gradient as Behavior Fingerprint: Stable Sequential Model Editing via Gradient Drift Regularization▲14k3.00
[PDF]When Samples Are Gone: Keeping Past Knowledge at Work for Lifelong Person Re-Identification▲3.0k2.33
Withdrawn or desk rejected (18)
[PDF]Retention Is Not Preservation: Budget-Matched Evaluation of Isofunctional Protein RewritingWithdrawn1.33
[PDF]SafeRoute: Retention-Constrained Local Evidence Control for Mixed-Shot RecognitionWithdrawn2.00
[PDF]Self-Induced Distribution Shift in Agent Memory: Write-Time Retention Criteria Cannot Be OptimalWithdrawn1.00