Related papers: Better Data Labelling with EMBLEM (and how that Im…
Labeling mistakes are frequently encountered in real-world applications. If not treated well, the labeling mistakes can deteriorate the classification performances of a model seriously. To address this issue, we propose an improved Naive…
Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…
Training and deploying machine learning models relies on a large amount of human-annotated data. As human labeling becomes increasingly expensive and time-consuming, recent research has developed multiple strategies to speed up annotation…
We present a novel AI-based ideation assistant and evaluate it in a user study with a group of innovators. The key contribution of our work is twofold: we propose a method of idea exploration in a constrained domain by means of…
In artificial intelligence (AI), the complexity of many models and processes surpasses human understanding, making it challenging to determine why a specific prediction is made. This lack of transparency is particularly problematic in…
Prompting LLMs offers an efficient way to guide output generation without explicit model training. In the e-commerce domain, prompting-based applications are widely used for tasks such as query understanding, recommender systems, and…
One of the best ways for developers to test and improve their skills in a fun and challenging way are programming challenges, offered by a plethora of websites. For the inexperienced ones, some of the problems might appear too challenging,…
There is a growing need for empirical benchmarks that support researchers and practitioners in selecting the best machine learning technique for given prediction tasks. In this paper, we consider the next event prediction task in business…
Programming is a core skill in computer science and software engineering (SE), yet identifying and resolving code errors remains challenging for both novice and experienced developers. While Large Language Models (LLMs) have shown…
Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that…
Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is…
Major advancements in computer vision can primarily be attributed to the use of labeled datasets. However, acquiring labels for datasets often results in errors which can harm model performance. Recent works have proposed methods to…
Over the past decade, Artificial Intelligence has significantly advanced, mostly driven by large-scale neural approaches. However, in the chemical process industry, where safety is critical, these methods are often unsuitable due to their…
We show that large pre-trained language models are inherently highly capable of identifying label errors in natural language datasets: simply examining out-of-sample data points in descending order of fine-tuned task loss significantly…
The SLAM paper demonstrated that on-device Small Language Models (SLMs) are a viable and cost-effective alternative to API-based Large Language Models (LLMs), such as OpenAI's GPT-4, offering comparable performance and stability. However,…
As demand for computer software continually increases, software scope and complexity become higher than ever. The software industry is in real need of accurate estimates of the project under development. Software development effort…
Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…
In natural language processing (NLP), the semantic similarity task requires large-scale, high-quality human-annotated labels for fine-tuning or evaluation. By contrast, in cases of music similarity, such labels are expensive to collect and…
Large Language Models (LLMs) pose a new paradigm of modeling and computation for information tasks. Recommendation systems are a critical application domain poised to benefit significantly from the sequence modeling capabilities and world…
Learning robot policies using imitation learning requires collecting large amounts of costly action-labeled expert demonstrations, which fundamentally limits the scale of training data. A promising approach to address this bottleneck is to…