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
275 results for “keyword:"unlearning"” in ICLR 2027. 60 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]UnlearnBench: A Clean and Controllable Benchmark for Fine-Grained and Compositional LLM Unlearning▼1.3k1.75
[PDF]FlowForget: Data Unlearning in Flow Matching Models via On-Policy Distillation and Preference Optimization
[PDF]Theory of Certified Unlearning for a Family of Regularization-Based Continual Learning▲5.4k3.00
[PDF]Linguistic Loopholes in LLM Unlearning: From a 174-Language–Script Benchmark to Coverage-Aware Unlearning▼4.5k2.67
[PDF]HPOD: Hierarchical Preference Optimization via On-Policy Distillation for LLM Concept Unlearning
[PDF]RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning▲13k2.33
[PDF]RWFUBench: A Cross-Domain Benchmark for Revealing Collateral Damage in Federated Unlearning▼4.3k2.00
[PDF]What Does It Mean to Forget a Person? Individual-Level Unlearning in Vision-Language Models▼4.3k2.00
[PDF]CSOA: Concept-Selective Adaptation with Semantic Control for Vision-Language Unlearning▲3952.67
[PDF]Reconstruct Then Rectify: Information-Conserving Node Interaction Estimation for Graph Unlearning▲9.2k2.67
Withdrawn or desk rejected (60)
[PDF]Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion ModelsWithdrawn1.67