Research
Research
Research
Research
3,865+ open-access research outputs.
In this note we formulate a conjecture about two group ring identities and prove that it would imply the Alon-Jaeger-Tarsi conjecture.…
Architectural floor plans are widely available priors which contain not only geometry but also the semantic information of the environment, yet existing localization methods largely ignore this semant…
This is the authors response to commentaries on the original article H is for Human and How (Not) to Evaluate Qualitative Research in HCI, https://doi.org/10.1080/07370024.2025.2475743 Commentaries we…
Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consistent step-by-step reasoning, especially in multili…
Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-building infrastructure. We present an agentic fra…
The plan existence problem asks, given a goal in the form of a formula in modal logic, an initial epistemic state (a pointed Kripke model), and a set of epistemic actions, whether there exists a seque…
We demonstrate a suspended thin-film aluminum nitride (AlN) microbolometer for narrowband very long-wave infrared detection. The device uses a 100-nm-thick AlN membrane suspended above a Pt back refle…
Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the…
Long-Horizon (LH) tasks in Human-Scene Interaction (HSI) are complex multi-step tasks that require continuous planning, sequential decision-making, and extended execution across domains to achieve the…
We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans t…
The 2015 fixed point result on rs-relational metric spaces due to Alam and Imdad [J. Fixed Point Th. Appl., 17 (2015), 693-702] is equivalent with the classical Banach Contraction Principle [Fund. Mat…
Let $G$ be an $n$-vertex graph with Laplacian eigenvalues $0=\lambda_1(G)\le \lambda_2(G)\le\cdots\le \lambda_n(G)$. Motivated by the Alon-Boppana bound and the Ramanujan phenomenon for regular graphs…
Large Language Models (LLMs) are prone to logical hallucinations and stochastic drifts during long-chain reasoning. While Classifier-Free Guidance (CFG) can improve instruction adherence, standard sta…
These notes are an expanded version of evening talks at the 2025 Georgia International Topology Conference, and an abbreviated version of talks at Georgia Tech, which were aimed at graduate students. …
Semiclassical analysis and noncommutative geometry are two pillars of quantum theory. It's only recently that bridges between them have been emerging. In this monograph, we combine various techniques …
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computationa…
We study the intersection statistics of affine subspaces in the hypercube $\mathbb{F}_2^n$, motivated by recent work of Alon, Axenovich, and Goldwasser on the intersection statistics of axis-aligned s…
Aluminum nitride (AlN)-based thin-film bulk acoustic wave resonators (FBARs) are promising compact platforms for 6G communications and quantum memory hardware, enabled by their integrable acoustic mod…
We present a quantitative framework for on-axis optical transduction of vertical InP nanowire resonators, correlating laser position to signal amplitude, calibration, and frequency stability. Photothe…
Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g.…
Free open-access publishing with Google Scholar indexing.
Submission Guide →