arXiv subjects

David Zhou

Publications and source records attributed to David Zhou.

8 recordsLinked to original sources

arXiv2026

IRIS: Navigating and Reflecting on Writing Traces Using Intelligent Document Histories

Much of the text produced throughout the lifetime of a document is impermanent. In this paper, we explore how writing activity traces can be made visible and interactive to help writers navigate their document histories and understand their writing processes. Using the Flower and Hayes cognitive process model of writing, IRIS infers writing process states from keystroke logs and presents them using an AI-enhanced version history. IRIS provides three primary interactions: revision highlighting that shows local process histories in-situ, conceptual filters that constrain the version history by process type or topic, and natural language inquiry that lets writers pose reflective questions about their writing and process. Following a formative and a longitudinal study, we find that writers use the interfaces to locate specific revisions and understand the progression of their writing. They use system outputs as interpretive material, relating them to pre-existing beliefs and confirming, challenging, and deepening their understanding of their writing.

cs.HC↗

arXiv2026

A Design Space for Live Music Agents

Live music provides a uniquely rich setting for studying creativity and interaction due to its spontaneous nature. The pursuit of live music agents--intelligent systems supporting real-time music performance and interaction--has captivated researchers across HCI, AI, and computer music for decades, and recent advancements in AI suggest unprecedented opportunities to evolve their design. However, the interdisciplinary nature of music has led to fragmented development across research communities, hindering effective communication and collaborative progress. In this work, we bring together perspectives from these diverse fields to map the current landscape of live music agents. Based on our analysis of 184 systems across both academic literature and video, we develop a comprehensive design space that categorizes dimensions spanning usage contexts, interactions, technologies, and ecosystems. By highlighting trends and gaps in live music agents, our design space offers researchers, designers, and musicians a structured lens to understand existing systems and shape future directions in real-time human-AI music co-creation. We release our annotated systems as a living artifact at https://live-music-agents.github.io.

cs.HC↗

arXiv2025

Thoughtful, Confused, or Untrustworthy: How Text Presentation Influences Perceptions of AI Writing Tools

AI writing tools have been shown to dramatically change the way people write, yet the effects of AI text presentation are not well understood nor always intentionally designed. Although text presentation in existing large language model interfaces is linked to the speed of the underlying model, text presentation speed can impact perceptions of AI systems, potentially influencing whether AI suggestions are accepted or rejected. In this paper, we analyze the effects of varying text generation speed in creative and professional writing scenarios on an online platform (n=297). We find that speed is correlated with perceived humanness and trustworthiness of the AI tool, as well as the perceived quality of the generated text. We discuss its implications on creative and writing processes, along with future steps in the intentional design of AI writing tool interfaces.

cs.HC↗

arXiv2024

Ai.llude: Encouraging Rewriting AI-Generated Text to Support Creative Expression

In each step of the creative writing process, writers must grapple with their creative goals and individual perspectives. This process affects the writer's sense of authenticity and their engagement with the written output. Fluent text generation by AIs risks undermining the reflective loop of rewriting. We hypothesize that deliberately generating imperfect intermediate text can encourage rewriting and prompt higher level decision making. Using logs from 27 writing sessions using a text generation AI, we characterize how writers adapt and rewrite AI suggestions, and show that intermediate suggestions significantly motivate and increase rewriting. We discuss the implications of this finding, and future steps for investigating how to leverage intermediate text in AI writing support tools to support ownership over creative expression.

cs.HC↗

arXiv2024

A Design Space for Intelligent and Interactive Writing Assistants

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

cs.HC↗

arXiv2024

Gamma-ray Bursts as Distance Indicators by a Statistical Learning Approach

Gamma-ray bursts (GRBs) can be probes of the early universe, but currently, only 26% of GRBs observed by the Neil Gehrels Swift Observatory GRBs have known redshifts ($z$) due to observational limitations. To address this, we estimated the GRB redshift (distance) via a supervised statistical learning model that uses optical afterglow observed by Swift and ground-based telescopes. The inferred redshifts are strongly correlated (a Pearson coefficient of 0.93) with the observed redshifts, thus proving the reliability of this method. The inferred and observed redshifts allow us to estimate the number of GRBs occurring at a given redshift (GRB rate) to be 8.47-9 $yr^{-1} Gpc^{-1}$ for $1.9<z<2.3$. Since GRBs come from the collapse of massive stars, we compared this rate with the star formation rate highlighting a discrepancy of a factor of 3 at $z<1$.

astro-ph.HE↗

arXiv2023

Ensuring User-side Fairness in Dynamic Recommender Systems

User-side group fairness is crucial for modern recommender systems, aiming to alleviate performance disparities among user groups defined by sensitive attributes like gender, race, or age. In the ever-evolving landscape of user-item interactions, continual adaptation to newly collected data is crucial for recommender systems to stay aligned with the latest user preferences. However, we observe that such continual adaptation often exacerbates performance disparities. This necessitates a thorough investigation into user-side fairness in dynamic recommender systems, an area that has been unexplored in the literature. This problem is challenging due to distribution shifts, frequent model updates, and non-differentiability of ranking metrics. To our knowledge, this paper presents the first principled study on ensuring user-side fairness in dynamic recommender systems. We start with theoretical analyses on fine-tuning v.s. retraining, showing that the best practice is incremental fine-tuning with restart. Guided by our theoretical analyses, we propose FAir Dynamic rEcommender (FADE), an end-to-end fine-tuning framework to dynamically ensure user-side fairness over time. To overcome the non-differentiability of recommendation metrics in the fairness loss, we further introduce Differentiable Hit (DH) as an improvement over the recent NeuralNDCG method, not only alleviating its gradient vanishing issue but also achieving higher efficiency. Besides that, we also address the instability issue of the fairness loss by leveraging the competing nature between the recommendation loss and the fairness loss. Through extensive experiments on real-world datasets, we demonstrate that FADE effectively and efficiently reduces performance disparities with little sacrifice in the overall recommendation performance.

cs.IR↗

arXiv2023

Class-Imbalanced Graph Learning without Class Rebalancing

Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. Most existing studies are rooted in a class-rebalancing (CR) perspective and address class imbalance with class-wise reweighting or resampling. In this work, we approach the root cause of class-imbalance bias from an topological paradigm. Specifically, we theoretically reveal two fundamental phenomena in the graph topology that greatly exacerbate the predictive bias stemming from class imbalance. On this basis, we devise a lightweight topological augmentation framework BAT to mitigate the class-imbalance bias without class rebalancing. Being orthogonal to CR, BAT can function as an efficient plug-and-play module that can be seamlessly combined with and significantly boost existing CR techniques. Systematic experiments on real-world imbalanced graph learning tasks show that BAT can deliver up to 46.27% performance gain and up to 72.74% bias reduction over existing techniques. Code, examples, and documentations are available at https://github.com/ZhiningLiu1998/BAT.

cs.LG↗