Related papers: Exploring the Challenges towards Lifelong Fact Lea…

The rise of misinformation underscores the need for scalable and reliable fact-checking solutions. Large language models (LLMs) hold promise in automating fact verification, yet their effectiveness across global contexts remains uncertain.…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames…

Factuality in Large Language Models (LLMs) is a persistent challenge. Current benchmarks often assess short factual answers, overlooking the critical ability to generate structured, multi-record tabular outputs from parametric knowledge. We…

This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the Factuality Issue as the…

Objective and scalable measurement of teaching quality is a persistent challenge in education. While Large Language Models (LLMs) offer potential, general-purpose models have struggled to reliably apply complex, authentic classroom…

This work addresses the problem of long-horizon task planning with the Large Language Model (LLM) in an open-world household environment. Existing works fail to explicitly track key objects and attributes, leading to erroneous decisions in…

This paper introduces a new fundamental characteristic, \ie, the dynamic range, from real-world metric tools to deep visual recognition. In metrology, the dynamic range is a basic quality of a metric tool, indicating its flexibility to…

Learning from Label Proportions (LLP) is an established machine learning problem with numerous real-world applications. In this setting, data items are grouped into bags, and the goal is to learn individual item labels, knowing only the…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in visual mathematical reasoning across various existing benchmarks. However, these benchmarks are predominantly based on clean or processed multimodal…

Zero-Shot Learning (ZSL) has attracted huge research attention over the past few years; it aims to learn the new concepts that have never been seen before. In classical ZSL algorithms, attributes are introduced as the intermediate semantic…

Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and generation models to augment text with relevant images. This…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains limited, primarily focusing on single-temporal or bi-temporal…

Continual learning (CL) is crucial for evaluating adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they…

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…

Lifelong learning remains an open problem. One of its main difficulties is catastrophic forgetting. Many dynamic expansion approaches have been proposed to address this problem, but they all use homogeneous models of predefined structure…

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model…

It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around:…

While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions-e.g., write a 10,000-word novel. Additionally,…

Large Language Models (LLMs) are increasingly adopted in educational contexts to provide personalized support to students and teachers. The unprecedented capacity of LLM-based applications to understand and generate natural language can…