相关论文: Comparing Native and Non-native English Speakers' …

Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method results in sub-optimal cross-modal alignment by…

The necessity for interpretability in natural language processing (NLP) has risen alongside the growing prominence of large language models. Among the myriad tasks within NLP, text generation stands out as a primary objective of…

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world…

We characterize 16 challenges faced by those investigating and developing remote and synchronous collaborative experiences around visualization. Our work reflects the perspectives and prior research efforts of an international group of 29…

This study introduces \textbf{InteractEval}, a framework that integrates human expertise and Large Language Models (LLMs) using the Think-Aloud (TA) method to generate attributes for checklist-based text evaluation. By combining human…

Active Learning (AL) addresses the high costs of collecting human annotations by strategically annotating the most informative samples. However, for subjective NLP tasks, incorporating a wide range of perspectives in the annotation process…

Sign languages are visual languages which convey information by signers' handshape, facial expression, body movement, and so forth. Due to the inherent restriction of combinations of these visual ingredients, there exist a significant…

Static Code Analysis (SCA) tools, while invaluable for identifying potential coding problems, functional bugs, or vulnerabilities, often generate an overwhelming number of warnings, many of which are non-actionable. This overload of alerts…

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of…

Software development is rarely an individual effort and generally involves teams of developers collaborating to generate good reliable code. Among the software code there exist technical dependencies that arise from software components…

Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human annotation effort in inducing a machine learning model. In a conventional active learning…

Recent developments in natural language generation (NLG) using neural language models have brought us closer than ever to the goal of building AI-powered creative writing tools. However, most prior work on human-AI collaboration in the…

What if the patterns hidden within dialogue reveal more about communication than the words themselves? We introduce Conversational DNA, a novel visual language that treats any dialogue -- whether between humans, between human and AI, or…

Spoken Language Understanding (SLU) plays a crucial role in speech-centric multimedia applications, enabling machines to comprehend spoken language in scenarios such as meetings, interviews, and customer service interactions. SLU…

We study the problem of detecting talking activities in collaborative learning videos. Our approach uses head detection and projections of the log-magnitude of optical flow vectors to reduce the problem to a simple classification of small…

We define "visual story-writing" as using visual representations of story elements to support writing and revising narrative texts. To demonstrate this approach, we developed a text editor that automatically visualizes a graph of entity…

This paper presents the results of the LegalLens Shared Task, focusing on detecting legal violations within text in the wild across two sub-tasks: LegalLens-NER for identifying legal violation entities and LegalLens-NLI for associating…

Large language models (LLMs) have diffused rapidly into academic writing since late 2022. Using the complete population of 109,393 research articles published in \textit{PLOS ONE} between 2019 and 2025, we examine population-level…

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…

Understanding the property of neural populations (or voxels) in the human brain can advance our comprehension of human perceptual and cognitive processing capabilities and contribute to developing brain-inspired computer models. Recent…