12 citations · 21 across the 13 of their papers we have counts for
16 papers
ConfTuner: Training Large Language Models to Express Their Confidence Verbally
Yibo Li, Miao Xiong, Jiaying Wu +1
Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare, where accurate expressions of uncertainty are essential for reli…
MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
Hui Chen, Miao Xiong, Yujie Lu +7
Recent advancements in AI agents have demonstrated their growing potential to drive and support scientific discovery. In this work, we introduce MLR-Bench, a comprehensive benchmar…
Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
Jiaying Wu, Fanxiao Li, Zihang Fu +2
The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators deliberately embed. Interpreting such creato…
Words or Vision: Do Vision-Language Models Have Blind Faith in Text?
Ailin Deng, Tri Cao, Zhirui Chen +1
Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplore…
Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection
Tri Cao, Minh-Huy Trinh, Ailin Deng +4
Anomaly detection (AD) is a machine learning task that identifies anomalies by learning patterns from normal training data. In many real-world scenarios, anomalies vary in severity…
ID: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition
Shen Li, Jianqing Xu, Jiaying Wu +7
Synthetic face recognition (SFR) aims to generate synthetic face datasets that mimic the distribution of real face data, which allows for training face recognition models in a priv…
FlipAttack: Jailbreak LLMs via Flipping
Yue Liu, Xiaoxin He, Miao Xiong +5
This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand t…
Proximity-Informed Calibration for Deep Neural Networks
Miao Xiong, Ailin Deng, Pang Wei Koh +4
Confidence calibration is central to providing accurate and interpretable uncertainty estimates, especially under safety-critical scenarios. However, we find that existing calibrat…
GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
Yuwen Li, Miao Xiong, Bryan Hooi
Label errors have been found to be prevalent in popular text, vision, and audio datasets, which heavily influence the safe development and evaluation of machine learning algorithms…
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
Ailin Deng, Miao Xiong, Bryan Hooi
Reliable application of machine learning is of primary importance to the practical deployment of deep learning methods. A fundamental challenge is that models are often unreliable…
Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness
Ailin Deng, Shen Li, Miao Xiong +2
Trustworthy machine learning is of primary importance to the practical deployment of deep learning models. While state-of-the-art models achieve astonishingly good performance in t…
Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation
Miao Xiong, Shen Li, Wenjie Feng +3
How do we know when the predictions made by a classifier can be trusted? This is a fundamental problem that also has immense practical applicability, especially in safety-critical…
Neural PCA for Flow-Based Representation Learning
Shen Li, Bryan Hooi
Of particular interest is to discover useful representations solely from observations in an unsupervised generative manner. However, the question of whether existing normalizing fl…
Probabilistic Contrastive Loss for Self-Supervised Learning
Shen Li, Jianqing Xu, Bryan Hooi
This paper proposes a probabilistic contrastive loss function for self-supervised learning. The well-known contrastive loss is deterministic and involves a temperature hyperparamet…
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
Ailin Deng, Bryan Hooi
Given high-dimensional time series data (e.g., sensor data), how can we detect anomalous events, such as system faults and attacks? More challengingly, how can we do this in a way…
Identifying through Flows for Recovering Latent Representations
Shen Li, Bryan Hooi, Gim Hee Lee
Identifiability, or recovery of the true latent representations from which the observed data originates, is de facto a fundamental goal of representation learning. Yet, most deep g…