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
645 results for “keyword:"robustness"” in ICLR 2027. 171 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VOICE OR LENGTH? COUNTERFACTUAL AUDITING OF TIMING SHORTCUTS IN AUDIO DEEPFAKE DETECTION▼1.2k1.67
[PDF]Freeze the Weights, Not the Graph: Prompt-Retrievable Watermarks for Frozen Diffusion Models with Certified Retrieval▼1361.33
[PDF]Target Fidelity in Time-Series Forecast Evaluation: A Controlled Study of Forecast Combinations▼1361.33
[PDF]Byzantine-Robust Federated Learning across Selection Strategies and Partial-Participation Regimes▼1361.33
[PDF]VocabAudit: Auditing Inference-Vocabulary Sensitivity in Training-Free Open-Vocabulary Segmentation▼5.8k2.33
[PDF]Probing Under Distribution Shift: Learning Generalizable Distributed Representations of LLM Activations▼5.8k2.33
[PDF]RGSM-GP: Reliability-Guided Semantic Memory for Iterative Graph Purification under Structural Attacks▲143.33
[PDF]Which Graph Is Safest? Predicting Adversarial Capture of LLM Agent Groups from Local Kernels▼4.3k2.00
[PDF]Same Knowledge, Different Graph: Knowledge-Graph Foundation Models Are Not Schema-Invariant▼4.5k2.67
[PDF]SeLo-Mark: Robust Localized Watermarking with Content-Derived Semantic Codes for Facial Integrity Verification▲5103.00
[PDF]Decorrelated Is Not Diversified: Style-Robust Selection and Search of Formulaic Alpha Factors▼1611.50
[PDF]Filtering Frozen World Models: Covariance-Aware Surprise and Better Forecasts at Test Time▼1361.33
[PDF]When Semantics Stay the Same but Predictions Change: Auditing Checkpoint Portability under Local Nominal Re-serialization▼1.2k1.67
[PDF]Action-Conditioned Predictive Consistency for Adversarial Detection in Vision-Language-Action Models▼4.3k2.00
[PDF]BoundaryWarp: Revealing and Exploiting Patch-End Vulnerabilities in Time-Series Foundation Models▼11k2.33
[PDF]EarthMind: Persistence-Anchored Latent Transitions for Robust Multimodal Earth Observation Forecasting▲11.00
[PDF]Disagreement Is Not Degradation: Evaluating Reliability in Multimodal Sentiment Analysis▼5.8k2.33
[PDF]Tightening Multimodal Regression Generalization Bounds via Structured Predictive Distributions▲3952.67
[PDF]DGMark: Dual-Granularity Composite Entropy for Robust Vocabulary Partitioning in Vision-Language Model Watermarking▼1361.33
[PDF]Disagreement Is Not Always Information: Task-Relevant Counterfactual Consensus Repair Under Multi-View Corruption▲6.1k2.00
[PDF]TransDiff: Plug-and-Play Adversarial Defense for No-Reference Image Quality Assessment via Calibrated Score Consensus▲5.4k3.00
[PDF]HyperRoGMAE: Multi-Scale Semantic Hypergraphs for Robust Graph Masked Autoencoder against Structural Attacks▲5.4k3.00
[PDF]Correctable Means Corruptible: The Reasoning Chain of Vision-Language-Action Policies Under Adaptive Attack▼4.3k2.00
Withdrawn or desk rejected (171)
[PDF]CLEAN-SPEECH TRANSPARENCY IS NOT DEPLOYMENT TRANSPARENCY: PREDICTING AND REPAIRING THE WORDS NEURAL AUDIO CODECS LOSE ON DEGRADED SPEECHWithdrawn1.00
[PDF]When Does Reference Purification Help? Contamination-Aware Representation Learning for Unsupervised Anomaly DetectionWithdrawn
[PDF]T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language ModelsWithdrawn2.00