Related papers: Dynamik: Syntactically-Driven Dynamic Font Sizing …
Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designed and model-based…
Text simplification is one of the domains in Natural Language Processing (NLP) that offers an opportunity to understand the text in a simplified manner for exploration. However, it is always hard to understand and retrieve knowledge from…
Effective decision-making often relies on timely insights from complex visual data. While Information Visualization (InfoVis) dashboards can support this process, they rarely adapt to users' cognitive state, and less so in real time. We…
Spoken language conveys meaning not only through words but also through intonation, emotion, and emphasis. Sentence stress, the emphasis placed on specific words within a sentence, is crucial for conveying speaker intent and has been…
People see text. Humans read by recognizing words as visual objects, including their shapes, layouts, and patterns, before connecting them to meaning, which enables us to handle typos, distorted fonts, and various scripts effectively.…
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…
The proliferation of misinformation in journalism, often stemming from flawed reasoning and logical fallacies, poses significant challenges to public understanding and trust in news media. Traditional fact-checking methods, while valuable,…
Neurodivergent people frequently experience decreased sound tolerance, with estimates suggesting it affects 50-70% of this population. This heightened sensitivity can provoke reactions ranging from mild discomfort to severe distress,…
Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism…
Traditional language models operate autoregressively, i.e., they predict one token at a time. Rapid explosion in model sizes has resulted in high inference times. In this work, we propose DynaMo, a suite of multi-token prediction language…
Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can…
The search task and the system both affect the demand on cognitive resources during information search. In some situations, the demands may become too high for a person. This article has a three-fold goal. First, it presents and critiques…
Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…
The Web has become a potentially infinite information resource, turning into an essential tool for many daily activities. This resulted in an increase in the amount of information available in users' contexts that is not taken into account…
Brain-inspired hyperdimensional computing (HDC) has been recently considered a promising learning approach for resource-constrained devices. However, existing approaches use static encoders that are never updated during the learning…
The emergence of programmable data-plane targets has motivated a new hybrid design for network streaming analytics systems that combine these targets' fast packet processing speeds with the rich compute resources available at modern stream…
Contextual memory integration remains a high challenge in the development of language models, particularly in tasks that require maintaining coherence over extended sequences. Traditional approaches, such as self-attention mechanisms and…
Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…
Our research introduces an innovative Natural Language Generation (NLG) approach that aims to optimize user experience and alleviate the workload of human customer support agents. Our primary objective is to generate informal summaries for…
The widespread use of digital devices has raised growing concerns about its impact on sustained attention at the population level. In this work, we propose a minimal dynamical framework to describe the collective evolution of attention…