Copertina

Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Chenruo, Tang, Kenan, Qin, Yao, Lei, Qi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
di: Liu, Chenruo, et al.
Pubblicazione: (2025)

Domain-invariant Clinical Representation Learning by Bridging Data Distribution Shift across EMR Datasets
di: Zhang, Zhongji, et al.
Pubblicazione: (2023)

Graphs Generalization under Distribution Shifts
di: Tian, Qin, et al.
Pubblicazione: (2024)

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
di: Hua, Andong, et al.
Pubblicazione: (2025)

Towards Understanding Link Predictor Generalizability Under Distribution Shifts
di: Revolinsky, Jay, et al.
Pubblicazione: (2024)

SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy
di: Zou, Xuecheng, et al.
Pubblicazione: (2026)

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro
di: Tang, Kenan, et al.
Pubblicazione: (2026)

Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
di: Wu, Jiayun, et al.
Pubblicazione: (2024)

Does Weak-to-strong Generalization Happen under Spurious Correlations?
di: Liu, Chenruo, et al.
Pubblicazione: (2025)

Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction
di: Badkul, Amitesh, et al.
Pubblicazione: (2025)

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
di: Zhang, Zeyang, et al.
Pubblicazione: (2024)

ExpressEdit: Fast Editing of Stylized Facial Expressions with Diffusion Models in Photoshop
di: Tang, Kenan, et al.
Pubblicazione: (2026)

Bias as a Virtue: Rethinking Generalization under Distribution Shifts
di: Chen, Ruixuan, et al.
Pubblicazione: (2025)

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
di: Hu, Yifan, et al.
Pubblicazione: (2025)

Causal-aware Graph Neural Architecture Search under Distribution Shifts
di: Li, Peiwen, et al.
Pubblicazione: (2024)

Alleviating Structural Distribution Shift in Graph Anomaly Detection
di: Gao, Yuan, et al.
Pubblicazione: (2024)

Sufficient Invariant Learning for Distribution Shift
di: Kim, Taero, et al.
Pubblicazione: (2022)

NeuroAI for AI Safety
di: Mineault, Patrick, et al.
Pubblicazione: (2024)

Supervised Algorithmic Fairness in Distribution Shifts: A Survey
di: Shao, Minglai, et al.
Pubblicazione: (2024)

Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
di: Wang, Tianyu, et al.
Pubblicazione: (2023)

Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
di: Zhang, Boxuan, et al.
Pubblicazione: (2026)

Weak-to-Strong Generalization under Distribution Shifts
di: Jeon, Myeongho, et al.
Pubblicazione: (2025)

Handling Distribution Shifts on Graphs: An Invariance Perspective
di: Wu, Qitian, et al.
Pubblicazione: (2022)

NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency
di: Yang, Shenzhi, et al.
Pubblicazione: (2025)

Foundations of Schrödinger Bridges for Generative Modeling
di: Tang, Sophia
Pubblicazione: (2026)

Dynamic Mixture of Experts Against Severe Distribution Shifts
di: Kim, Donghu
Pubblicazione: (2025)

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
di: Chen, Mouxiang, et al.
Pubblicazione: (2023)

Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture
di: Burden, John, et al.
Pubblicazione: (2025)

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
di: Elboher, Yizhak Yisrael, et al.
Pubblicazione: (2025)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
di: Chen, Yiwei, et al.
Pubblicazione: (2025)

Emerging Synergies in Causality and Deep Generative Models: A Survey
di: Zhou, Guanglin, et al.
Pubblicazione: (2023)

GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
di: Zou, Deyu, et al.
Pubblicazione: (2023)

Addressing Label Shift in Distributed Learning via Entropy Regularization
di: Wu, Zhiyuan, et al.
Pubblicazione: (2025)

Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
di: Zeng, Fanlong, et al.
Pubblicazione: (2025)

Robust Calibration For Improved Weather Prediction Under Distributional Shift
di: Gilda, Sankalp, et al.
Pubblicazione: (2024)

Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts
di: Yang, Jinluan, et al.
Pubblicazione: (2024)

FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Prediction
di: Xu, Muhao, et al.
Pubblicazione: (2024)

Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
di: Chen, Qin, et al.
Pubblicazione: (2025)

A Semi-Automated Solution Approach Recommender for a Given Use Case: a Case Study for AI/ML in Oncology via Scopus and OpenAI
di: Kılıç, Deniz Kenan, et al.
Pubblicazione: (2023)

Shutdown Safety Valves for Advanced AI
di: Conitzer, Vincent
Pubblicazione: (2026)