Related papers: HEIDL: Learning Linguistic Expressions with Deep L…

Many real-world applications of language models (LMs), such as writing assistance and code autocomplete, involve human-LM interaction. However, most benchmarks are non-interactive in that a model produces output without human involvement.…

Accessible and inclusive design has gained increased attention in HCI, yet practical implementation remains challenging due to resource-intensive prototyping methods. Traditional approaches such as workshops, A-B tests, and co-design…

Pre-trained and frozen large language models (LLMs) can effectively map simple scene rearrangement instructions to programs over a robot's visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural…

Human reasoning can be understood as a cooperation between the intuitive, associative "System-1" and the deliberative, logical "System-2". For existing System-1-like methods in visual activity understanding, it is crucial to integrate…

While scaling individual Large Language Models (LLMs) has delivered remarkable progress, the next frontier lies in scaling collaboration through multi-agent systems (MAS). However, purely autonomous MAS remain ''closed-world'' systems,…

High-quality human annotations are necessary for creating effective machine learning-driven stream processing systems. We study hybrid stream processing systems based on a Human-In-The-Loop Machine Learning (HITL-ML) paradigm, in which one…

Due to the limited smartness and abilities of machine intelligence, currently autonomous vehicles are still unable to handle all kinds of situations and completely replace drivers. Because humans exhibit strong robustness and adaptability…

The interactive machine learning (IML) community aims to augment humans' ability to learn and make decisions over time through the development of automated decision-making systems. This interaction represents a collaboration between…

Recent years have witnessed increasing interests in developing interpretable models in Natural Language Processing (NLP). Most existing models aim at identifying input features such as words or phrases important for model predictions.…

Recent human-object interaction detection (HOID) methods highly require prior knowledge from vision-language models (VLMs) to enhance the interaction recognition capabilities. The training strategies and model architectures for connecting…

Interpreting hierarchical structures latent in language is a key limitation of current language models (LMs). While previous research has implicitly leveraged these hierarchies to enhance LMs, approaches for their explicit encoding are yet…

Despite significant progress in autonomous vehicles (AVs), the development of driving policies that ensure both the safety of AVs and traffic flow efficiency has not yet been fully explored. In this paper, we propose an enhanced…

Despite growing interest in using large language models (LLMs) to automate annotation, their effectiveness in complex, nuanced, and multi-dimensional labelling tasks remains relatively underexplored. This study focuses on annotation for the…

Large language models (LLMs) increasingly mimic human cognition in various language-based tasks. However, their capacity for metacognition - particularly in predicting memory performance - remains unexplored. Here, we introduce a…

Building models for realistic natural language tasks requires dealing with long texts and accounting for complicated structural dependencies. Neural-symbolic representations have emerged as a way to combine the reasoning capabilities of…

Predicting human behavior in shared environments is crucial for safe and efficient human-robot interaction. Traditional data-driven methods to that end are pre-trained on domain-specific datasets, activity types, and prediction horizons. In…

Evaluating the capability of Large Language Models (LLMs) in following instructions has heavily relied on a powerful LLM as the judge, introducing unresolved biases that deviate the judgments from human judges. In this work, we reevaluate…

The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML…

In-Context Learning (ICL) is a significant paradigm for Large Multimodal Models (LMMs), using a few in-context demonstrations (ICDs) for new task adaptation. However, its performance is sensitive to demonstration configurations and…

Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challenging. In this work, we show that pre-trained large language…