arXiv preprints from January 1, 2026 through September 22, 2026 — 09:16:09 EST
Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance. It motivated the study of principled approaches for domain alignment, such as optimal transport based unsupervised domain adaptation, that relies on approximating Monge map using transport...
Recent reports on generative AI chatbot use raise concerns about its addictive potential. An in-depth understanding is imperative to minimize risks, yet AI chatbot addiction remains poorly understood. This study examines how to characterize AI chatbot addiction--why users become addicted, the symptoms commonly reported, and the...
Language Identification (LID), the task of determining the language of a given text, is a fundamental preprocessing step that shapes the reliability of downstream NLP applications. While recent work has expanded African LID, existing systems remain limited in both language coverage and fine-grained discrimination among closely related...
Artificial Intelligence (AI) applications, such as Large Language Models, are primarily driven and executed by Graphics Processing Units (GPUs). These GPU programs (kernels) consume substantial amounts of energy, yet software developers often lack the hardware expertise and ad hoc knowledge required to optimize for power efficiency....
People often have things they want to say but hold back in conversations, fearing vulnerability or social consequences. Online, this restraint can take a distinctive form: even when such thoughts are written out - in moments of anger, guilt, or longing - people may choose to withhold them, leaving them unsent. This process is...
In the study of Human-Computer Interaction, privacy is often seen as a core issue, and it has been explored directly in connection with User Interface (UI) and User Experience (UX) design. We systematically investigate the key considerations and factors for privacy in UI/UX, drawing upon the extant literature and 15 semi-structured...
Commutativity reasoning based on Lipton's movers is a powerful technique for verification of concurrent programs. The idea is to define a program transformation that preserves a subset of the initial set of interleavings, which is sound modulo reorderings of commutative actions. Scaling commutativity reasoning to routinely-used...
As multiple robots are expected to coexist in future households, natural language is increasingly envisioned as a primary medium for human-robot and robot-robot communication. This paper introduces the concept of a Natural Language Environment (NLE), defined as an interaction space in which humans and multiple heterogeneous robots...
This paper presents SEER, an upgraded version of our prior method Context Is All You Need for detecting Gang of Four (GoF) design patterns from source code. The earlier approach modeled code as attention-ready sequences that blended lightweight structure with behavioral context; however, it lacked explicit role disambiguation within...
Spatial transcriptomics (ST) enables transcriptome-wide profiling while preserving the spatial context of tissues, offering unprecedented opportunities to study tissue organization and cell-cell interactions in situ. Despite recent advances, existing methods often lack effective integration of histological morphology with molecular...
Across the social and medical sciences, researchers recognize that specifying planned research activities (i.e., 'registration') prior to the commencement of research has benefits for both the transparency and rigour of science. Despite this, evidence suggests that study registrations frequently go unexamined, minimizing their...
Relative to English, low-resource languages suffer from substantial tokenization premiums in modern LMs, meaning that it generally requires several times as many tokens to encode a sentence in a low-resource language than to encode the analogous sentence in English. This tokenization premium results in increased API and energy costs...
We present PepEDiff, a novel peptide binder generator that designs binding sequences given a target receptor protein sequence and its pocket residues. Peptide binder generation is critical in therapeutic and biochemical applications, yet many existing methods rely heavily on intermediate structure prediction, adding complexity and...
The peer review process is essential to the success of science, but it also delays publications and absorbs considerable effort. Journals find it increasingly difficult to recruit competent reviewers. This study presents the results of agent-based simulation that models the current peer review process. We compared it to the simulation...
We present a unified deductive verification framework for first-order temporal properties based on well-founded rankings, where verification conditions are discharged using SMT solvers. To that end, we introduce a novel reduction from verification of arbitrary temporal properties to verification of termination. Our reduction augments...
Dialectal Arabic (DA) speech data vary widely in domain coverage, dialect labeling practices, and recording conditions, complicating cross-dataset comparison and model evaluation. To characterize this landscape, we conduct a computational analysis of linguistic ``dialectness'' alongside objective proxies of audio quality on the...
Climate discourse online shapes public understanding of climate change and informs political and policy debate, yet it unfolds across structurally different environments: paid advertising platforms host targeted, institutionally produced messaging, while public social media reflects largely organic, user-driven discussion. We present...
Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, current multimodal large language models (MLLMs) cannot do this, as they remain largely restricted to static spatial perception, struggling to answer "what-if"...
Robustness verification of neural networks, referring to formally proving that neural networks satisfy robustness properties, is of crucial importance in safety-critical applications, where model failures can result in loss of human life or million-dollar damages. However, the dependability of verification results may be questioned...
Benchmarking large language models (LLMs) is critical for understanding their capabilities, limitations, and robustness. In addition to interface artifacts, prior studies have shown that LLM decisions can be influenced by directive signals such as social cues, framing, and instructions. In this work, we introduce option injection, a...
We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By capturing hierarchical component relationships, connections, and semantic elements across diverse engineering domains, our proposed dataset would enable...
Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI agents increasingly collaborate on complex work, they must develop coordination capabilities to function as effective teammates. Yet we hypothesize that current agents lack these...
Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production environments, particularly within regulated domains such as healthcare and pharmaceuticals. In these settings, systems must balance competing requirements, including minimizing inference latency for real-time clinical decision...
Telegram has become one of the leading platforms for disseminating misinformational messages. However, many existing pipelines still classify each message's credibility based on the reputation of its associated domain names or its lexical features. Such methods work well on traditional long-form news articles published by well-known...
Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operational complexity. We instead reuse computation already paid for by the serving LLM: we train lightweight probes on its hidden states and predict labels in the same forward pass used for...