Digital Commons Network^™

Variational Speculative Decoding: Rethinking Draft Training From Token Likelihood To Sequence Acceptance, Xiandong Zou, Jianshu Li, Jing Huang, Pan Zhou

Research Collection School Of Computing and Information Systems

Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves verifying and ranking multiple sampled draft paths. We propose Variational Speculative Decoding (VSD), formulating draft training as variational inference over latent proposals (draft paths). VSD maximizes the marginal probability of target-model acceptance, yielding an ELBO that promotes high-quality latent proposals while minimizing divergence from the target distribution. To enhance quality and reduce variance, we incorporate a path-level utility and optimize via an Expectation-Maximization procedure. The E-step draws MCMC samples from an oracle-filtered posterior, while the M-step maximizes weighted likelihood using …

Dual-Diffusional Generative Fashion Recommendation, Mingzhe Yu, Lei Wu, Qianru Sun, Yunshan Ma

Research Collection School Of Computing and Information Systems

Personalized generative recommender systems have emerged as a promising solution for fashion recommendation. However, existing methods primarily rely on implicit visual embeddings from historical interactions, which often contain preference-irrelevant information and result in insufficient user behavior modeling. Moreover, these models typically generate only item images, providing limited interpretability. To address these limitations, we propose DualFashion, a Dual-Diffusional Generative Fashion Recommendation Architecture that jointly models image and text modalities for personalized and explainable recommendation. DualFashion adopts a dual-diffusion Transformer with image and text branches, where structured attribute-level captions and visual outfit information are jointly used as conditioning signals to model user …

Itimo: An Llm-Empowered Synthesis Dataset For Travel Itinerary Modification, Zhuoxuan Huang, Yunshan Ma, Hongyu Zhang, Hua Ma, Zhu Sun

Research Collection School Of Computing and Information Systems

Addressing itinerary modification is crucial for enhancing the travel experience as it is a frequent requirement during traveling. However, existing research mainly focuses on fixed itinerary planning, leaving modification underexplored due to the scarcity of shape need-to-modify itinerary data. To bridge this gap, we formally define the itinerary modification task and propose a general pipeline to construct the corresponding dataset, namely iTIMO. This pipeline frames the generation of shape need-to-modify itinerary data as an intent-driven perturbation task. It instructs large language models to perturb real-world itineraries using three operations: REPLACE, ADD, and DELETE. Each perturbation is grounded in three intents: …

Multimodal Contrastive Spatiotemporal Self-Organizing Neural Networks For In-Home Activity Learning Of Mild Cognitive Impairment, Seng Khoon Teh, Ah-Hwee Tan, Kar Way Tan, Iris Rawtaer

Research Collection School Of Computing and Information Systems

In-home spatiotemporal data, such as the movement trajectory data and the spatial time series data, contains potential predictive utility for detection of geriatric conditions including Mild Cognitive Impairment (MCI), frailty, and cognitive frailty. However, few have explored spatiotemporal learning models for learning and fusion of such disparate spatiotemporal data, owing to the lack of a generalized machine learning model that can jointly model these different spatiotemporal data types. This work reports a multimodal spatiotemporal machine learning model based on a class of self-organizing neural networks that can integrate different spatiotemporal data types for MCI detection. Specifically, Episodic Memory Adaptive Resonance …

Configuring Agentic Ai Coding Tools: An Exploratory Study, Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar, Christoph Treude, Sebastian Baltes

Research Collection School Of Computing and Information Systems

Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration mechanisms for agentic AI coding tools, covering Claude Code, GitHub Copilot, Cursor, Gemini, and Codex. We identify eight configuration mechanisms spanning from static context to executable and external integrations and, in an empirical study of 2,853 GitHub repositories, examine whether and how they are adopted, with a detailed analysis of Context Files, Skills, and Subagents. First, Context Files dominate the configuration landscape and are often the sole mechanism in …

A Framework For Top-K Queries With Constrained Preferences, Kyriakos Mouratidis, Nikolaos Chaloulakos, Bo Tang

Research Collection School Of Computing and Information Systems

Traditional rank-aware processing assumes a dataset that contains available options to cover a specific need (e.g., restaurants, hotels, etc) and users who browse that dataset via top-k queries with linear scoring functions, i.e., by ranking the options according to the weighted sum of their attributes, for a set of given weights. In practice, however, user preferences (weights) may only be estimated with bounded accuracy, or may be inherently imprecise due to the inability of a human user to specify exact weight values with absolute accuracy. Motivated by this, we define the constrained-preference top-k (CT) query. Given an approximate description of …

Oscbench: Benchmarking Object State Change In Text-To-Video Generation, Xianjing Han, Bin Zhu, Shiqi Hu, Franklin Mingzhe Li, Patrick Carrington, Roger Zimmermann, Jingjing Chen

Research Collection School Of Computing and Information Systems

Text-to-video (T2V) generation models have made rapid progress in producing visually high-quality and temporally coherent videos. However, existing benchmarks primarily focus on perceptual quality, text–video alignment, or physical plausibility, leaving a critical aspect of action understanding largely unexplored: object state change (OSC) explicitly specified in the text prompt. OSC refers to the transformation of an object’s state induced by an action, such as peeling a potato or slicing a lemon. In this paper, we introduce OSCBench, a benchmark specifically designed to assess OSC performance in T2V models. OSCBench is constructed from instructional cooking data and systematically organizes action–object interactions into …

Larger Is Not Always Better: Exploring Small Open-Source Language Models In Logging Statement Generation, Renyi Zhong, Yichen Li, Guangba Yu, Wenwei Gu, Jinxi Kuang, Yintong Huo, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Developers use logging statements to create logs that document system behavior and aid in software maintenance. As such, high-quality logging is essential for effective maintenance; however, manual logging often leads to errors and inconsistency. Recent methods emphasize using large language models (LLMs) for automated logging statement generation, but these present privacy and resource issues, hindering their suitability for enterprise use. This paper presents the first large-scale empirical study evaluating small open-source language models (SOLMs) for automated logging statement generation. We evaluate four prominent SOLMs using various prompt strategies and parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation …

Constrained Assortment Optimization Under The Mixed-Logit Model, Hoang Giang Pham, Tien Mai

Research Collection School Of Computing and Information Systems

In this paper, we study the assortment optimization problem under the mixed-logit customer choice model. While assortment optimization has been a central topic in revenue management for decades, the mixed-logit model is widely regarded as one of the most general and flexible frameworks for modeling and predicting customer purchasing behavior. The assortment optimization problem is known to be NP-hard to be approximated to any constant factor, even in the unconstrained case. To address this challenge, we first explore the submodularity properties of a simplified version of the objective function to derive novel semi-constant factor approximation solutions for assortment problems under …

Survey On Learning-Based Dynamic Fault Localization: From Traditional Machine Learning To Large Language Models, Chunyan Liu, Yan Lei, Huan Xie, Jinping Wang, Yue Yu, David Lo

Research Collection School Of Computing and Information Systems

Learning-based dynamic fault localization techniques play a crucial role in the field of software engineering. These techniques dynamically execute test cases to meticulously extract useful knowledge from the execution information in the program, with the aim of identifying fault locations by leveraging machine learning, deep learning, and large language models. Currently, there is already a flourishing body of research that is intensely focused on learning-based dynamic fault localization. Research literature can be categorized into two main aspects for learning-based dynamic fault localization: data-based enhancements (i.e., the datasets) and model-based enhancements (i.e., the suspiciousness algorithms). Thus, we conduct an extensive literature …

Air: Improving Agent Safety Through Incident Response, Zibo Xiao, Jun Sun, Junjie Chen

Research Collection School Of Computing and Information Systems

Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost exclusively on preventing failures in advance, providing limited capabilities for responding to, containing, or recovering from incidents after they inevitably arise. In this work, we introduce AIR, the first incident response framework for LLM agent systems. AIR defines a domain-specific language for managing the incident response lifecycle autonomously in LLM agent systems, and integrates it into the agent's execution loop to (1) detect incidents via semantic checks grounded in the current environment state and …

Math 119: Math For Elementary School Teachers Instructor Guide, Seth Lehman

Open Educational Resources

OER instructor guide for Math 119: Math for Elementary School Teachers at Queens College

How Do Different Food Influents Affect Biogas Production, Process And Operational Stability, And System Performance In The Armfield W8, A Bench-Scale Anaerobic Digester, Jarko Rumbaoa, Anahita Adhikari

Rose-Hulman Undergraduate Research Publications

No abstract provided.

Center Of Mass (Com) Shift In Electric Vertical Takeoff And Landing (Evtol) Aircraft, Irene Lema Madueno

Rose-Hulman Undergraduate Research Publications

No abstract provided.

Sustainable Extraction Of A New Diketopiperazine, Anthony Chapman

Rose-Hulman Undergraduate Research Publications

No abstract provided.

Native Plants For Green Roofs In Indiana, Alasdair Curts

Rose-Hulman Undergraduate Research Publications

No abstract provided.

2026 July - Tennessee Monthly Climate Report, Tennessee Climate Office, East Tennessee State University

Tennessee Climate Office Monthly Reports

Hi All,

Heavy rains, flooding, and a few heat waves defined the month of July across Tennessee. The rainfall continued to improve drought conditions across the state but flooding impacted many areas, including parts of East Tennessee on July 12th with Cocke County reporting six landslides and infrastructure damage in many locations. A strong heatwave impacted the state during the first week of July and another heatwave impacted western TN in late July.

Mean temperatures for July 2026 were above the NOAA 1991-2020 climate normals for the month across Tennessee, with most areas of West and Middle Tennessee averaging 1-2°F …

2026 July - Tennessee Climate Snapshot, Tennessee Climate Office, East Tennessee State University

Tennessee Climate Office Monthly Reports

No abstract provided.

Draft Final 2023 Insufficiently Reclaimed Sites Sampling: Bres No. 93 – Soudan Dump Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final 2023 Unreclaimed Sites Sampling: Ur-42 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

On The Side And Angle Mixtures Expressed By Triangles: Phase Diagrams Based On Intensive State Properties, Daniel Graham

Chemistry: Faculty Publications and Other Works

This is a lecture packet focused on the side and angle mixtures of structures at the center of the planar geometry universe. The intensive states of triangles are charted with the help of phase diagrams—long-standing tools in chemical thermodynamics and materials science. The intended audience consists of students and teachers—college and high school—seeking fresh perspectives, projects, and discussion topics surrounding age-old systems.

Improving Urban Search And Rescue Team Coordination Through Adaptive Context Awareness, Daniel Reyes Duran

Doctoral Dissertations and Master's Theses

Modern multi-agent Urban Search and Rescue (USAR) operations heavily rely on mobile geospatial Common Operating Pictures (COPs) to maintain team coordination and Situational Awareness (SA). However, the proliferation of high-frequency sensor telemetry at the tactical edge has introduced a data saturation paradox challenge: while information theoretically drives informed decision-making, unmanaged data surges induce increased operator cognitive overload and alert fatigue on mobile End-User Devices (EUDs), while downstream data-broadcasting models inherently strain edge processing and viewport environments.

To resolve these constraints, this dissertation presents a context-aware Value of Information (VoI) data-management framework integrated directly with a custom, event-driven Android Team Awareness …

Book Review: Atlas Of Minerals And Igneous And Metamorphic Rocks In Thin-Section (2025) By Alessandro Da Mommio And Victoria Pease., Kenneth L. Brown

Geology and Environmental Geoscience Faculty Publications

"Optical mineralogy and petrography not only equip us with the skills necessary to address society’s growing need for rock and mineral resources but also awaken a deeper curiosity—inviting us into moments of discovery that change the way we understand these resources. From observing the vibrant and mesmerizing interference colors of a dunite thin section to examining the uniaxial interference figure of calcite, many of us can still recall the first time we peered through the oculars of a polarizing microscope. Atlas of Minerals and Igneous and Metamorphic Rocks in Thin-Section is an exceptional reference textbook, which nurtures that curiosity and …

Quantization Dimension For A Generalized Inhomogeneous Bi-Lipschitz Iterated Function System, Shivam Dubey, Mrinal Kanti Roychowdhury, Saurabh Verma

School of Mathematical & Statistical Sciences Faculty Publications

For a given r∈(0,+∞), the quantization dimension of order r, if it exists, denoted by Dr(μ), of a Borel probability measure μ on R^d represents the speed how fast the nth quantization error of order r approaches to zero as the number of elements n in an optimal set of n-means for μ tends to infinity. If Dr(μ) does not exists, we call D̲r(μ) and D¯r(μ), the lower and upper quantization dimensions of μ of order r. In this paper, we estimate the quantization dimension of condensation measures associated with condensation systems ({fi}i=1^N,(pi)i=0^N,ν), where the …

On The True Interstellar Anisotropy Of Tev Cosmic Rays And Its Implications For The Local Interstellar Medium, Noufel D. Maalal

Theses and Dissertations

Several ground-based cosmic ray (CR) air shower experiments have produced sky maps of intensity anisotropy in the energy range from 1 TeV to a few hundred TeVs with very high statistics and angular resolution. These measurements provide opportunities to study CR sources and propagation in the interstellar medium (ISM). Such studies present two major difficulties. Firstly, CRs are deflected by the heliospheric magnetic field on the last stretch of their journey to Earth. Secondly, measurements at different latitudes are difficult to compare, leading to uncertainties in latitudinal variations on the order of the observed anisotropy. Experiments usually assume latitudinal variations …

Mechanistic And Spatio-Temporal Modelling Of Cassava Whitefly (Bemisia Tabaci) Risk Under Climate Change: Projections For Africa With Case Evidence From Malawi, Lumbani Benedicto Banda, Frank Thomas Ndjomatchoua, Ritter A. Guimapi, Komi Mensah Agboka, Abdelmutalab G.A. Azrag, Wezi G. Mhango, Trust Kasambala Donga, Chikondi Makwiza, Karl H. Thunes, Elfatih M. Abdel-Rahman

All Peer-Reviewed Publications

The cassava whitefly (Bemisia tabaci) greatly constrains cassava production across Africa due to its role as a vector of viral diseases that cause substantial yield losses. Effective management of this insect pest requires detailed knowledge of its spatio-temporal distribution, however long-term datasets are scarce. Mechanistic models circumvent these long-term data needs by modelling temperature-dependent processes that govern population dynamics. Nevertheless, their application to B. tabaci remains poorly explored. Here, we developed a mechanistic model to derive a risk index (RI) for B. tabaci across Africa, focusing on Malawi. The model integrates the effects of temperature on the life stages of …

Environmental And Socioeconomic Effects Of Roundtable On Sustainable Palm Oil Certification: A Systematic Review And Meta-Analysis, Kibrom T. Sibhatu, Matin Qaim

All Peer-Reviewed Publications

Palm oil is the most widely produced and consumed vegetable oil worldwide, but its production is associated with deforestation and other environmental and social problems. Roundtable on Sustainable Palm Oil (RSPO) is the only internationally-recognized voluntary certification standard aimed at mitigating such problems. Many studies examine RSPO’s effects on particular outcomes in specific contexts, but a consolidated global assessment is lacking. Here, we systematically review the literature and identify 53 original studies covering RSPO effects in various countries of Asia, Africa, and Latin America. Where data availability permits, we also conduct meta-analysis. Results reveal that RSPO can lead to environmental …

Late-Night And Early-Morning Train Scheduling With Non-Traffic Hour Maintenance Window In Urban Rail Transit Systems, Yaochen Ma, Hai Yang, Hai Wang

Research Collection School Of Computing and Information Systems

Regular maintenance during non-traffic hours (NTH) is vital for the resilience of urban rail transit (URT) systems, yet an insufficient NTH maintenance window poses a challenge for URT systems in various cities. For instance, the Hong Kong MTR Corporation has noted that the required NTH maintenance time often exceeds the available window, prompting service adjustments such as earlier late-night closures and/or later early-morning starts. To address this challenge, this study develops an optimal scheduling framework that links late-night and early-morning URT services through the NTH maintenance window requirement to maximize public welfare. A Decoupled Optimization Model (DOM) first derives closed-form …

Deep Learning For Video Anomaly Detection: A Review, Peng Wu, Chengyu Pan, Yuting Yan, Guansong Pang, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnessed much good progress. In the era of deep learning, with the explosion of architectures of continuously growing capability and capacity, a great variety of deep learning-based methods are constantly emerging for the VAD task, greatly improving the generalization ability of detection algorithms and broadening the application scenarios. Therefore, such a multitude of methods and a large body of literature make a comprehensive survey a pressing necessity. In this article, we present …

Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning, Brahmanage Janaka Chathuranga Thilakarathna, Akshat Kumar

Research Collection School Of Computing and Information Systems

Sequential decision-making using Markov Decision Process underpins many real-world applications. Both model-based and model-free methods have achieved strong results in these settings. However, real-world tasks must balance reward maximization with safety constraints, often conflicting objectives, that can lead to unstable min–max, adversarial optimization. A promising alternative is safety reachability analysis, which precomputes a forward-invariant safe state–action set, ensuring that an agent starting inside this set remains safe indefinitely. Yet, most reachability-based methods address only hard safety constraints, and little work extends reachability to cumulative cost constraints. To address this, first, we define a safety-conditioned reachability set that decouples reward maximization …