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
67 results for “keyword:"harm"” in ICLR 2027. 18 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]A Harmful Request Is Still a Request: Benign Fine-Tuning Rewrites How Aligned Models Begin to Answer▲3972.67
[PDF]Ratio-RFE: From Appearance Fitting to Source-Relative Relighting Field Estimation for Image Harmonization▲5103.00
[PDF]FAPA: A Dual-Branch Framework for Time Series Forecasting with Frequency Amplitude Shaping and Harmonic Period Alignment▼4.3k2.00
[PDF]Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection▼1.2k1.67
[PDF]Misaligned model variants serve as an effective source of training for harm detection probes▲5103.00
[PDF]When Conversation is the Attack: Mining Transferable Contexts for Harmful Compliance and Over-Refusal▲3.0k2.33
[PDF]Beyond Jailbreak Rates: Harm Centric Evaluation of Multi Turn Jailbreak Attacks and Defenses▼4.3k2.00
[PDF]When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations▲5.4k3.00
[PDF]MedDAC: Learning Directional Communication via Correction and Harm Modeling for Medical Multi-Agent Reasoning▼5.8k2.33
[PDF]Beyond Static Pockets: Benchmarking and Modeling Multi-State Transporter Drug Discovery▼4.3k2.00
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]AC-Diff: Anatomy–Contrast Disentangled Diffusion for Multi-Vendor Liver MRI Harmonization▲6.1k2.00
[PDF]PharmEval: A Diagnostic Benchmark for Pharmacological Knowledge and Reasoning of Large Language Models▼5.8k2.33
[PDF]SafetyTransfer: Distilling Harmful and Harmless Discrimination for Selective Refusal in Small Language Models▼4.3k2.00
[PDF]Alzheimer's Disease Classification via Score-Derived Spectral Coupling from Longitudinal Cortical Data▲3972.67
Withdrawn or desk rejected (18)
[PDF]Beyond the Final Token: Detecting Jailbreak Prompts via Chat-Suffix-Probed Safety TrajectoriesWithdrawn1.67
[PDF]SE(3)-EQUIVARIANT ACOUSTIC GRAPH OPERATORS: PHYSICAL FOUNDATIONS, STEERABLE MESSAGE PASSING, AND ZERO-SHOT SPATIAL ARRAY GENERALIZATIONDesk rejected
[PDF]SHield: Watermarking 4D Gaussian Splatting via Spherical Harmonic Coefficient PerturbationWithdrawn1.67
[PDF]From Cellular Responses to Pharmacological Domains: Multimodal Zero-Shot Drug Representation LearningWithdrawn2.00
[PDF]Safety Alignment Under Language Shift: Harmful Compliance, Over-Refusal, and Response-Language Dynamics in Low-Resource LanguagesDesk rejected1.67