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
399 results for “keyword:"editing"” in ICLR 2027. 156 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SPECTRA: Source-Preserving Editing with Cross-Scale Transform and Representation Adaptation▼4.3k2.00
[PDF]When Does an Edit Become Unsafe? Tracing Safety Emergence Along the Generative Trajectory of Image Editing Models▼4.3k2.00
[PDF]Bidirectional Transfer, Asymmetric Expression: Math Fine-Tuning Conceals the Code Gains It Carries▲13k2.33
[PDF]SpiderAudio: Unified Binaural Representation for Joint Spatial Speech Understanding, Generation and Editing▼4.3k2.00
[PDF]Bridging the Representation–Behavior Gap in Knowledge Editing with Calibrated Activation Steering▲6.1k2.00
[PDF]User Message Fine-tuning: Implanting Beliefs, Preferences, and Alignment in LLMs by Training on User Messages▲3972.67
[PDF]TS-Edit: A Model Editing Framework for Adversarial Defense in Time-Series Foundation Models▼1361.33
[PDF]TIMELINE-BENCH: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final Cut▼5.8k2.33
[PDF]Deterministic Addresses Constrain Reads, Not Ordinary Writes: Deletion Boundaries in Conditional-Memory Language Models▲6.1k2.00
[PDF]Reinforcing Large Vision Language Models for Multi-Hop Reasoning in Lifelong Knowledge Editing▼5.8k2.33
[PDF]Path-Space: Estimating Transformer Component Effects and Their Interactions from Shared Backward Passes▼5.8k2.33
[PDF]UAR-LoRA: Uncertainty-Aware Rank-Adaptive Low-Rank Adaptation for Lifelong Knowledge Editing▼1.2k1.67
[PDF]CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences▲3972.67
Withdrawn or desk rejected (156)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33