Search Results for author:
Found 27 papers, 18 papers with code
Advancing Conversational Diagnostic AI with Multimodal Reasoning
Large Language Models (LLMs) have demonstrated great potential for conducting diagnostic conversations but evaluation has been largely limited to language-only interactions, deviating from the real-world requirements of remote care delivery.
Towards Conversational AI for Disease Management
We advance the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE) through a new LLM-based agentic system optimised for clinical management and dialogue, incorporating reasoning over the evolution of disease and multiple patient visit encounters, response to therapy, and professional competence in medication prescription.
Conformalized Credal Regions for Classification with Ambiguous Ground Truth
An open question in \emph{Imprecise Probabilistic Machine Learning} is how to empirically derive a credal region (i. e., a closed and convex family of probabilities on the output space) from the available data, without any prior knowledge or assumption.
Capabilities of Gemini Models in Medicine
We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable, often by a wide margin.
Ranked #1 on
Question Answering
on MedQA
(using extra training data)
Mitigating LLM Hallucinations via Conformal Abstention
We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e. g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or incorrect answer.
Conformalized Credal Set Predictors
Credal sets are sets of probability distributions that are considered as candidates for an imprecisely known ground-truth distribution.
Certified Robust Models with Slack Control and Large Lipschitz Constants
In this paper, we propose a Calibrated Lipschitz-Margin Loss (CLL) that addresses this issue and improves certified robustness by tackling two problems: Firstly, commonly used margin losses do not adjust the penalties to the shrinking output distribution; caused by minimizing the Lipschitz constant $K$.
Unlocking Accuracy and Fairness in Differentially Private Image Classification
The poor performance of classifiers trained with DP has prevented the widespread adoption of privacy preserving machine learning in industry.
Conformal prediction under ambiguous ground truth
However, in many real-world scenarios, the labels $Y_1,..., Y_n$ are obtained by aggregating expert opinions using a voting procedure, resulting in a one-hot distribution $\mathbb{P}_{vote}^{Y|X}$.
Evaluating AI systems under uncertain ground truth: a case study in dermatology
Our approach boils down to generating multiple samples of medical condition probabilities, then evaluating and averaging performance metrics based on these sampled probabilities.
Robustifying Token Attention for Vision Transformers
Interestingly, we observe that the attention mechanism of ViTs tends to rely on few important tokens, a phenomenon we call token overfocusing.
Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions
Despite their success, vision transformers still remain vulnerable to image corruptions, such as noise or blur.
On Fragile Features and Batch Normalization in Adversarial Training
In order to shed light on the role of BN in adversarial training, we investigate to what extent the expressiveness of BN can be used to robustify fragile features in comparison to random features.
Improving Robustness by Enhancing Weak Subnets
We show that EWS greatly improves both robustness against corrupted images as well as accuracy on clean data.
Learning Optimal Conformal Classifiers
However, using CP as a separate processing step after training prevents the underlying model from adapting to the prediction of confidence sets.
A Closer Look at the Adversarial Robustness of Information Bottleneck Models
We study the adversarial robustness of information bottleneck models for classification.
Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators
Moreover, we present a novel adversarial bit error attack and are able to obtain robustness against both targeted and untargeted bit-level attacks.
Relating Adversarially Robust Generalization to Flat Minima
To this end, we propose average- and worst-case metrics to measure flatness in the robust loss landscape and show a correlation between good robust generalization and flatness.
Bit Error Robustness for Energy-Efficient DNN Accelerators
Low-voltage operation of DNN accelerators allows to further reduce energy consumption significantly, however, causes bit-level failures in the memory storing the quantized DNN weights.
Adversarial Training against Location-Optimized Adversarial Patches
Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB.
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
Our confidence-calibrated adversarial training (CCAT) tackles this problem by biasing the model towards low confidence predictions on adversarial examples.
Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training
Adversarial training is the standard to train models robust against adversarial examples.
Disentangling Adversarial Robustness and Generalization
A recent hypothesis even states that both robust and accurate models are impossible, i. e., adversarial robustness and generalization are conflicting goals.
Learning 3D Shape Completion From Laser Scan Data With Weak Supervision
Learning-based approaches, in contrast, avoid the expensive optimization step and instead directly predict the complete shape from the incomplete observations using deep neural networks.
Learning 3D Shape Completion under Weak Supervision
We address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics.
Superpixels: An Evaluation of the State-of-the-Art
As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison.
