Poster "safety-critical applications" Papers

12 papers found

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese et al.

ICML 2025arXiv:2505.23968
2
citations

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

Zitong Shi, Guancheng Wan, Haixin Wang et al.

NEURIPS 2025

Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation

Moru Liu, Hao Dong, Jessica Kelly et al.

NEURIPS 2025arXiv:2505.16985
4
citations

Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning

Kyowoon Lee, Jaesik Choi

ICML 2025arXiv:2506.00867
4
citations

Safety Representations for Safer Policy Learning

Kaustubh Mani, Vincent Mai, Charlie Gauthier et al.

ICLR 2025arXiv:2502.20341
1
citations

Support is All You Need for Certified VAE Training

Changming Xu, Debangshu Banerjee, Deepak Vasisht et al.

ICLR 2025arXiv:2504.11831

Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction

Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann et al.

ECCV 2024arXiv:2403.07263
19
citations

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

Alaa Anani, Tobias Lorenz, Bernt Schiele et al.

ICML 2024arXiv:2402.08400
2
citations

A Provable Decision Rule for Out-of-Distribution Detection

Xinsong Ma, Xin Zou, Weiwei Liu

ICML 2024

Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment

Muhammad Sohail Danish, Muhammad Haris Khan, Muhammad Akhtar Munir et al.

CVPR 2024arXiv:2405.14497
25
citations

Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation

Dapeng Hu, Jian Liang, Xinchao Wang et al.

ICML 2024

VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees

Anahita Baninajjar, Ahmed Rezine, Amir Aminifar

ICML 2024arXiv:2312.09748
1
citations