Poster "distribution shift robustness" Papers

15 papers found

Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability

Divya Jyoti Bajpai, Manjesh Kumar Hanawal

NEURIPS 2025arXiv:2509.23666
1
citations

Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition

Xinyu Tian, Shu Zou, Zhaoyuan Yang et al.

ICLR 2025arXiv:2502.15809
5
citations

Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport

Jiawei Huang, Minming Li, Hu Ding

NEURIPS 2025

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

Changdae Oh, Yixuan Li, Kyungwoo Song et al.

ICLR 2025arXiv:2410.03782
16
citations

Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation

Shohei Enomoto

NEURIPS 2025arXiv:2510.07823

Generative Classifiers Avoid Shortcut Solutions

Alexander Li, Ananya Kumar, Deepak Pathak

ICLR 2025arXiv:2512.25034
12
citations

Latent Space Factorization in LoRA

Shashi Kumar, Yacouba Kaloga, John Mitros et al.

NEURIPS 2025arXiv:2510.19640

Precise Diffusion Inversion: Towards Novel Samples and Few-Step Models

Jing Zuo, Luoping Cui, Chuang Zhu et al.

NEURIPS 2025

Sufficient Invariant Learning for Distribution Shift

Taero Kim, Subeen Park, Sungjun Lim et al.

CVPR 2025arXiv:2210.13533
3
citations

Test-Time Visual In-Context Tuning

Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr et al.

CVPR 2025arXiv:2503.21777
4
citations

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses

Sahar Dastani, Ali Bahri, Gustavo Vargas Hakim et al.

NEURIPS 2025arXiv:2509.22813

Visual Instruction Bottleneck Tuning

Changdae Oh, Jiatong Li, Shawn Im et al.

NEURIPS 2025arXiv:2505.13946
3
citations

Learning Divergence Fields for Shift-Robust Graph Representations

Qitian Wu, Fan Nie, Chenxiao Yang et al.

ICML 2024arXiv:2406.04963
2
citations

Robust Data-driven Prescriptiveness Optimization

Mehran Poursoltani, Erick Delage, Angelos Georghiou

ICML 2024arXiv:2306.05937
2
citations

WARM: On the Benefits of Weight Averaged Reward Models

Alexandre Rame, Nino Vieillard, Léonard Hussenot et al.

ICML 2024