Related papers: CatAlyst: Domain-Extensible Intervention for Preve…

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach to progressively generate a sequence of tasks as curricula to facilitate reinforcement learning in hard-exploration problems. At the heart of our approach, a task…

Modern large language models (LLMs) are capable of interpreting input strings as instructions, or prompts, and carry out tasks based on them. Unlike traditional learners, LLMs cannot use back-propagation to obtain feedback, and condition…

This study investigates whether assessments fostering higher-order thinking skills can reduce plagiarism involving generative AI tools. Participants completed three tasks of varying complexity in four groups: control, e-textbook, Google,…

Large Language Models (LLMs) such as ChatGPT have demonstrated remarkable performance across various tasks and have garnered significant attention from both researchers and practitioners. However, in an educational context, we still observe…

This workshop paper presents a critical examination of the integration of Generative AI (Gen AI) into the academic writing process, focusing on the use of AI as a collaborative tool. It contrasts the performance and interaction of two AI…

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and…

The rapid integration of large language models (LLMs) into everyday workflows has transformed how individuals perform cognitive tasks such as writing, programming, analysis, and multilingual communication. While prior research has focused…

Sensemaking in collaborative work and learning is increasingly supported by GenAI systems, however, emerging evidence suggests that poorly designed GenAI systems tend to provide explicit instruction that groups passively follow, fostering…

Large language models (LLMs) have gained significant attention in various fields but prone to hallucination, especially in knowledge-intensive (KI) tasks. To address this, retrieval-augmented generation (RAG) has emerged as a popular…

Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously…

Recent breakthroughs in artificial intelligence have driven a paradigm shift, where large language models (LLMs) with billions or trillions of parameters are trained on vast datasets, achieving unprecedented success across a series of…

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…

Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence, yet evaluating RAG systems in specialized, safety-critical domains remains a significant challenge. Existing…

High throughput experimentation tools, machine learning (ML) methods, and open material databases are radically changing the way new materials are discovered. From the experimentally driven approach in the past, we are moving quickly…

The primary way of building AI applications is shifting from training specialist models to prompting generalist models. A common practice for prompting generalist models, often referred to as in-context learning, is to append a few examples…

Recently, parallel text generation has received widespread attention due to its success in generation efficiency. Although many advanced techniques are proposed to improve its generation quality, they still need the help of an…

Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with generated pseudo…

State-of-the-art visual generative AI tools hold immense potential to assist users in the early ideation stages of creative tasks -- offering the ability to generate (rather than search for) novel and unprecedented (instead of existing)…

This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance…

Developmental AI creates embodied AIs that develop human-like abilities. The AIs start with innate competences and learn more by interacting with the world including people. Developmental AIs have been demonstrated, but their abilities so…