Search Results for author:
Found 12 papers, 0 papers with code
RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting
While Multimodal Large Language Models (MLLMs) have made remarkable progress in vision-language reasoning, they are also more susceptible to producing harmful content compared to models that focus solely on text.
Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models
With the rapid advancement of Large Language Models (LLMs), significant safety concerns have emerged.
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
However, recent research shows that the visual modality in VLMs is highly vulnerable, allowing attackers to bypass safety alignment in LLMs through visually transmitted content, launching harmful attacks.
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Based on Chinese SimpleQA, we perform a comprehensive evaluation on the factuality abilities of existing LLMs.
Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment
Our method improves the success rate on adversarial samples by 10\% compared to the sample-wise approach, and achieves a 1. 3\% improvement on evaluation benchmarks such as MMLU, GSM8K, HumanEval, etc.
Safety Alignment for Vision Language Models
To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images.
Generalizing Fault Detection Against Domain Shifts Using Stratification-Aware Cross-Validation
Incipient anomalies present milder symptoms compared to severe ones, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions.
Using Ensemble Classifiers to Detect Incipient Anomalies
Incipient anomalies present milder symptoms compared to severe ones, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions.
Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
Ensemble learning is widely applied in Machine Learning (ML) to improve model performance and to mitigate decision risks.
Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?
Intermediate-Severity (IS) faults present milder symptoms compared to severe faults, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions.
Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults
The Monte Carlo dropout method has proved to be a scalable and easy-to-use approach for estimating the uncertainty of deep neural network predictions.
An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
We show that the encoder-decoder model is able to identify the injected anomalies in a modern manufacturing process in an unsupervised fashion.
