Related papers: ChatGPT and general-purpose AI count fruits in pic…
ChatGPT is a publicly available chatbot that can quickly generate texts on given topics, but it is unknown whether the chatbot is really superior to human writers in all aspects of writing and whether its writing quality can be prominently…
We present a method for generating large numbers of isomorphic physics problems using generative AI services such as ChatGPT, through prompt chaining and tool use. This approach enables precise control over structural variations-such as…
The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need fine-tuning on…
An in-depth comprehension of global land cover is essential in Earth observation, forming the foundation for a multitude of applications. Although remote sensing technology has advanced rapidly, leading to a proliferation of satellite…
A particularly successful class of approaches for few-shot learning combines language models with prompts -- hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires…
Despite remarkable advancements in few-shot generalization in natural language processing, most models are developed and evaluated primarily in English. To facilitate research on few-shot cross-lingual transfer, we introduce a new…
Campus climate surveys play a pivotal role in capturing how students, faculty, and staff experience university life, yet traditional methods frequently suffer from low participation and minimal follow-up. We present TigerGPT, a new AI…
Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language…
Post-harvest fruit quality assessment is essential for reducing food waste, yet reliable non-destructive methods typically depend on expensive hyperspectral cameras and computationally intensive deep learning models. These systems typically…
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for…
The number of objects is considered an important factor in a variety of tasks in the agricultural domain. Automated counting can improve farmers decisions regarding yield estimation, stress detection, disease prevention, and more. In recent…
With the rise of online education platforms, there is a growing abundance of educational content across various domain. It can be difficult to navigate the numerous available resources to find the most suitable training, especially in…
Deep learning models can encounter unexpected failures, especially when dealing with challenging sub-populations. One common reason for these failures is the occurrence of objects in backgrounds that are rarely seen during training. To gain…
Few-shot detection-based counters estimate the number of instances in the image specified only by a few test-time exemplars. A common approach to localize objects across multiple sizes is to merge backbone features of different resolutions.…
Prevailing methods for mapping large generative language models to supervised tasks may fail to sufficiently probe models' novel capabilities. Using GPT-3 as a case study, we show that 0-shot prompts can significantly outperform few-shot…
We present CROP (Central Roundish Object Painter), which identifies and paints the object at the center of an RGB image. Primarily CROP works for roundish fruits in various illumination conditions, but surprisingly, it could also deal with…
Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress.This paper presents…
Entity Matching is the task of deciding if two entity descriptions refer to the same real-world entity. State-of-the-art entity matching methods often rely on fine-tuning Transformer models such as BERT or RoBERTa. Two major drawbacks of…
The success of large pre-trained object detectors hinges on their adaptability to diverse downstream tasks. While fine-tuning is the standard adaptation method, specializing these models for challenging fine-grained domains necessitates…
Few-shot object detection aims to detect instances of specific categories in a query image with only a handful of support samples. Although this takes less effort than obtaining enough annotated images for supervised object detection, it…