Nathalie Rauschmayr — accepted AI-conference papers

2025

Gatekeeper: Improving Model Cascades Through Confidence Tuning

Stephan Rabanser, Nathalie Rauschmayr, Achin Kulshrestha, Petra Poklukar, Wittawat Jitkrittum, Sean Augenstein +2

NeurIPS 2025poster

Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these challenges, local smaller models are often deployed alongside larger models, relying on routing and deferral mechanisms to o…

Cited by 0 Source ↗Scholar ↗

2025

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Shangbin Feng, Zifeng Wang, Yike Wang, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich +6

ICML 2025poster

We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM exp…

Cited by 6 Source ↗PDF ↗Scholar ↗

2025

Test-Time Visual In-Context Tuning

Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele

CVPR 2025poster

Visual in-context learning (VICL), as a new paradigm in computer vision, allows the model to rapidly adapt to various tasks with only a handful of prompts and examples. While effective, the existing VICL paradigm exhibits poor generalizability under distribution shifts. In this work, we propose test…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Extracting Training Data From Document-Based VQA Models

Francesco Pinto, Nathalie Rauschmayr, Florian Tramèr, Philip Torr, Federico Tombari

ICML 2024poster

Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can memorize responses for training samples and regurgitate them even…

Cited by 7 Source ↗PDF ↗Scholar ↗

2022

Generating Distributional Adversarial Examples to Evade Statistical Detectors

Yigitcan Kaya, Muhammad Bilal Zafar, Sergul Aydore, Nathalie Rauschmayr, Krishnaram Kenthapadi

ICML 2022spotlight

Deep neural networks (DNNs) are known to be highly vulnerable to adversarial examples (AEs) that include malicious perturbations. Assumptions about the statistical differences between natural and adversarial inputs are commonplace in many detection techniques. As a best practice, AE detectors are ev…

Cited by 7 Source ↗PDF ↗Scholar ↗