Latest AI and machine learning research in clinical trials for healthcare professionals.
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific knowledge in training data, has been widely used in privacy protection. However, MU for safety in MLLM has yet to be fully explored. To address this issue, we propose SAFEERASER, a safety unlearning benc...
AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content through text prompts. Examples of such tools include large language models (LLMs) and text-to-image (T2I) diffusion models. As the performance of various leadin...
Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and...
With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment. Current ben...
The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerabi...
Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nu...
Clinical trials remain critical in cardiac drug development but face high failure rates due to efficacy limitations and safety risks, incurring subs...
The calibration of high-quality two-qubit entangling gates is an essential component in engineering large-scale, fault-tolerant quantum computers. H...
Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primar...
Post-training quantization (PTQ) has emerged as a promising solution for reducing the storage and computational cost of vision transformers (ViTs). ...
Randomized experiments are the preferred approach for evaluating the effects of interventions, but they are costly and often yield estimates with su...
The Cox proportional hazards model is often used for model development in data from randomized controlled trials (RCT) with time-to-event outcomes. ...
There is mounting interest in the possibility that metformin, indicated for glycemic control in type 2 diabetes, has a range of additional beneficial ...
Iterative Krylov projection methods have become widely used for solving large-scale linear inverse problems. However, methods based on orthogonality...
In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR d...
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has re...
Hamilton-Jacobi (HJ) reachability is a rigorous mathematical framework that enables robots to simultaneously detect unsafe states and generate actio...
BACKGROUND: The efficacy of laminectomy procedures is contingent on the method of resection. The objective of this study was to investigate the impact...
Protein structure holds immense potential for pathogenicity prediction, albeit structure-based predictors are limited compared to the sequence-based c...
BACKGROUND: High-stress environments, heavy workloads, and the emotional demands of patient care, which are common challenges faced by nurses, are fac...