相关论文: Human Uncertainty-Aware Data Selection and Automat…

Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing…

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varies widely across…

Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…

Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we…

Deep neural network models can learn clinically relevant features from millions of histopathology images. However generating high-quality annotations to train such models for each hospital, each cancer type, and each diagnostic task is…

Large Language Models (LLMs) have demonstrated remarkable progress in instruction following and general-purpose reasoning. However, achieving high-quality alignment with human intent and safety norms without human annotations remains a…

Technological and computational advances continuously drive forward the broad field of deep learning. In recent years, the derivation of quantities describing theuncertainty in the prediction - which naturally accompanies the modeling…

Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-language models (VLMs) can be leveraged to further reduce…

This paper investigates the automation of qualitative data analysis, focusing on inductive coding using large language models (LLMs). Unlike traditional approaches that rely on deductive methods with predefined labels, this research…

Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality ground truth for training. Recent work has shown that prompt tuning of vision-language…

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that…

The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, unmeasured variables, such as confounders, break this…

Data analysis is a crucial analytical process to generate in-depth studies and conclusive insights to comprehensively answer a given user query for tabular data. In this work, we aim to propose new resources and benchmarks to inspire future…

Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated uncertainty with guarantees. Split conformal prediction (SCP) offers finite-sample…

Recent Vision-based Large Language Models~(VisionLLMs) for autonomous driving have seen rapid advancements. However, such promotion is extremely dependent on large-scale high-quality annotated data, which is costly and labor-intensive. To…

This study addresses the critical challenge of hallucination mitigation in Large Vision-Language Models (LVLMs) for Visual Question Answering (VQA) tasks through a Split Conformal Prediction (SCP) framework. While LVLMs excel in multi-modal…

Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended meaning. Although prior work has proposed…

Key frame selection in video understanding presents significant challenges. Traditional top-K selection methods, which score frames independently, often fail to optimize the selection as a whole. This independent scoring frequently results…

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…