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
280 results for “keyword:"unlearn"” in ICLR 2027. 62 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels▲5.4k3.00
[PDF]Removing Sequentially Trained Modules: Effects on Retained Sources and Subsequent Learning▼1611.50
[PDF]Forget the Fact, Keep the Form: Distribution Redistribution for Retain-Free Unlearning in Masked Diffusion Language Models▼4.3k2.00
[PDF]What Survives Unlearning? Calibrated Subject-Level Auditing of Residual Knowledge in LLMs▲3.8k2.50
[PDF]Rethinking Anti-distillation of Large Language Models: An Unlearnable Examples Perspective▲5103.00
[PDF]RAQUEL: Robust Evaluation of Machine Unlearning Through Queries over Aligned Databases▼1.3k1.75
[PDF]Deterministic Addresses Constrain Reads, Not Ordinary Writes: Deletion Boundaries in Conditional-Memory Language Models▲6.1k2.00
[PDF]FedCoDS: Federated LLM Unlearning by Coupling Knowledge Distillation with Likelihood Suppression▲3.8k2.50
[PDF]Blind by Construction: Record-Level Unlearning Audits Miss Retained-Carrier Reconstruction on Frozen Time-Series Features▼1611.50
[PDF]Analyzing LLM Unlearning: Token-Triggered Forgetting Mechanism and Entity-Weighted Remedy for Trigger-Free Queries▲3952.67
[PDF]When Unlearning Is Not the End: Controlled Oracle Recovery Against Federated Unlearning▼1.2k1.67
Withdrawn or desk rejected (62)
[PDF]Probe-Geometry Alignment: Auditing and Suppressing Representational Memorization in Language ModelsWithdrawn1.25
[PDF]Concepts Persist as Directions: Visual-State Auditing of Unlearned Diffusion ModelsWithdrawn1.67