Related papers: Using Transformers to Provide Teachers with Person…
Social coding platforms, such as GitHub, serve as laboratories for studying collaborative problem solving in open source software development; a key feature is their ability to support issue reporting which is used by teams to discuss tasks…
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants. However, the standard methodology of evaluating LLMs relies on static pairs of inputs and outputs,…
Video-based programming tutorials are a popular form of tutorial used by authors to guide learners to code. Still, the interactivity of these videos is limited primarily to control video flow. There are existing works with increased…
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…
The scarcity of large-scale classroom speech data has hindered the development of AI-driven speech models for education. Classroom datasets remain limited and not publicly available, and the absence of dedicated classroom noise or Room…
Task-oriented dialogue is difficult in part because it involves understanding user intent, collecting information from the user, executing API calls, and generating helpful and fluent responses. However, for complex tasks one must also…
As human-robot collaboration advances, natural and flexible communication methods are essential for effective robot control. Traditional methods relying on a single modality or rigid rules struggle with noisy or misaligned data as well as…
Self-talk-an internal dialogue that can occur silently or be spoken aloud-plays a crucial role in emotional regulation, cognitive processing, and motivation, yet has remained largely invisible and unmeasurable in everyday life. In this…
Mathematical formulas are a fundamental and widely used component in various scientific fields, serving as a universal language for expressing complex concepts and relationships. While state-of-the-art transformer models excel in processing…
Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to…
Adaptive scaffolding enhances learning, yet the field lacks robust methods for measuring it within authentic tutoring dialogue. This gap has become more pressing with the rise of remote human tutoring and large language model-based systems.…
Large language models (LLMs) are, by design, inherently capable of multi-task learning: through a unified next-token prediction paradigm, they can naturally address a wide variety of downstream tasks. Prior work in the motion domain has…
Talking-head video editing aims to efficiently insert, delete, and substitute the word of a pre-recorded video through a text transcript editor. The key challenge for this task is obtaining an editing model that generates new talking-head…
Visual Question-Answering, a technology that generates textual responses from an image and natural language question, has progressed significantly. Notably, it can aid in tracking and inquiring about daily activities, crucial in healthcare…
Accurate and efficient prediction of polymer properties is of great significance in polymer design. Conventionally, expensive and time-consuming experiments or simulations are required to evaluate polymer functions. Recently, Transformer…
The Transformer model, initially achieving significant success in the field of natural language processing, has recently shown great potential in the application of tactile perception. This review aims to comprehensively outline the…
Introducing new technologies such as messaging platforms, and the chatbots attached to them, in higher education, is rapidly growing. This introduction entails a careful consideration of the potential opportunities and/or challenges of…
Recent Speech-to-Speech Translation (S2ST) systems achieve strong semantic accuracy yet consistently strip away non-verbal vocalizations (NVs), such as laughter and crying that convey pragmatic intent, which severely limits real-world…
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers of self-attention that allow them to capture long range…
Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue…