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
61 results for “keyword:"model editing"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TS-Edit: A Model Editing Framework for Adversarial Defense in Time-Series Foundation Models▼1361.33
[PDF]Deterministic Addresses Constrain Reads, Not Ordinary Writes: Deletion Boundaries in Conditional-Memory Language Models▲6.1k2.00
[PDF]Path-Space: Estimating Transformer Component Effects and Their Interactions from Shared Backward Passes▼5.8k2.33
[PDF]Shape the Residuals, Not the Update: Spectrally Constrained Batch Editing for Subject-Centric Knowledge▲5103.00
[PDF]Edit the Model You Deploy: Quantization Weakens Knowledge Edits Through Their Conditioning▼1361.33
[PDF]RefusalTrace: Localizing and Validating the Internal Refusal Pathway of LLMs with Sparse Autoencoder Features▲9.7k2.75
[PDF]RUR-Edit: Instance-Aware Residual Allocation and Utility-Aware Update Reconstruction for Knowledge Editing▼4.3k2.00
[PDF]SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors▼4.5k2.67