Related papers: K$\alpha$LOS finds Consensus: A Meta-Algorithm for…
Large Language Models (LLMs) are increasingly used in Spoken Language Understanding (SLU), where effective multimodal learning depends on the alignment between audio and text. Despite various fusion methods, no standard metric exists to…
Human annotation remains the foundation of reliable and interpretable data in Natural Language Processing (NLP). As annotation and evaluation tasks continue to expand, from categorical labelling to segmentation, subjective judgment, and…
Supervised machine learning assumes that labeled data provide accurate measurements of the concepts models are meant to learn. Yet in practice, human labeling introduces systematic variation arising from ambiguous items, divergent…
With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming,…
RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…
In object recognition applications, object images usually appear with different quality levels. Practically, it is very important to indicate object image qualities for better application performance, e.g. filtering out low-quality object…
Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more…
Object detection (OD) in computer vision has made significant progress in recent years, transitioning from closed-set labels to open-vocabulary detection (OVD) based on large-scale vision-language pre-training (VLP). However, current…
Despite recent advances in multimodal pre-training for visual description, state-of-the-art models still produce captions containing errors, such as hallucinating objects not present in a scene. The existing prominent metric for object…
Data in real-world object detection often exhibits the long-tailed distribution. Existing solutions tackle this problem by mitigating the competition between the head and tail categories. However, due to the scarcity of training samples,…
Recent works have emerged in multi-annotator learning that shift focus from Consensus-oriented Learning (CoL), which aggregates multiple annotations into a single ground-truth prediction, to Individual Tendency Learning (ITL), which models…
A multi-agent system (MAS) enhances its capacity to solve complex natural language processing (NLP) tasks through collaboration among multiple agents, where consensus-seeking serves as a fundamental mechanism. However, existing…
The search for suitable datasets is the critical "first step" in data-driven research, but it remains a great challenge. Researchers often need to search for datasets based on high-level task descriptions. However, existing search systems…
Reliable benchmarking is critical for advancing Vision-Language-Action (VLA) models, as it reveals their generalization, robustness, and alignment of perception with language-driven manipulation tasks. However, existing benchmarks often…
Large language models (LLMs) often fail to synthesize information from their context to generate an accurate response. This renders them unreliable in knowledge intensive settings where reliability of the output is key. A critical component…
We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in…
Object detection (OD), a crucial vision task, remains challenged by the lack of large training datasets with precise object localization labels. In this work, we propose ALWOD, a new framework that addresses this problem by fusing active…
Label noise remains a challenge for training robust classification models. Most methods for mitigating label noise have been benchmarked using primarily datasets with synthetic noise. While the need for datasets with realistic noise…
Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…
Schema matching is a core data integration task, focusing on identifying correspondences among attributes of multiple schemata. Numerous algorithmic approaches were suggested for schema matching over the years, aiming at solving the task…