arXiv preprints from January 1, 2026 through July 20, 2026 — 04:35:08 EST
Large Language Models (LLMs) are rapidly reshaping scientific research. We analyze these changes in multiple, large-scale datasets with 2.1M preprints, 28K peer review reports, and 246M online accesses to scientific documents. We find: 1) scientists adopting LLMs to draft manuscripts demonstrate a large increase in paper production,...
Conversational AI is rapidly becoming a primary interface for information seeking and decision making, yet most systems still assume idealized users. In practice, human reasoning is bounded by limited attention, uneven knowledge, and reliance on heuristics that are adaptive but bias-prone. This article outlines a research pathway...
Pervasive sensing in industrial and underground environments is severely constrained by airborne dust, smoke, confined geometry, and metallic structures, which rapidly degrade optical and LiDAR based perception. Elevation resolved 4D mmWave radar offers strong resilience to such conditions, yet there remains a limited understanding of...
The public confidence and trust in online healthcare information have been greatly dented following the COVID-19 pandemic, which triggered a significant rise in online health misinformation. Existing literature shows that different datasets have been created to aid with detecting false information associated with this COVID infodemic....
The European Union Artificial Intelligence (EU AI) Act, which explicitly references fundamental rights and ethical principles, is a comprehensive regulatory framework for governing Artificial Intelligence (AI) systems. This study examines the moral grounding of the EU AI Act by analyzing the semantic alignment between three...
A fundamental challenge in text-to-3D face generation is achieving high-quality geometry. The core difficulty lies in the arbitrary and intricate distribution of vertices in 3D space, making it challenging for existing models to establish clean connectivity and resulting in suboptimal geometry. To address this, our core insight is to...
As reasoning modules, such as the chain-of-thought mechanism, are applied to large language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now is to assess the uncertainty of answers, which can help prevent misleading or serious...
Optimal Causation Entropy (oCSE) is a robust causal network modeling technique that reveals causal networks from dynamical systems and coupled oscillators, distinguishing direct from indirect paths. CausationEntropy is a Python package that implements oCSE and several of its significant optimizations and methodological extensions. In...
This paper introduces a novel methodology for generating controlled, multi-level dust concentrations in a highly cluttered environment representative of harsh, enclosed environments, such as underground mines, road tunnels, or collapsed buildings, enabling repeatable mm-wave propagation studies under severe electromagnetic...
Long-horizon navigation in unstructured environments demands terrain abstractions that scale to tens of km$^2$ while preserving semantic and geometric structure, a combination existing methods fail to achieve. Grids scale poorly; quadtrees misalign with terrain boundaries; neither encodes landcover semantics essential for...
Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.g., "Sure, here is how to...") at the start of an LLM's output and lead the model to continue the response. We make two contributions to this prior work. First, we show that an unsophisticated adversary can improve the...
Scale does not uniformly improve reasoning - it restructures it. Analyzing 25,000+ chain-of-thought trajectories across four domains (Law, Science, Code, Math) and two scales (8B, 70B parameters), we discover that neural scaling laws trigger domain-specific phase transitions rather than uniform capability gains. Legal reasoning...
State Space Models (SSMs) and Hidden Markov Models (HMMs) are foundational frameworks for modeling sequential data with latent variables and are widely used in signal processing, control theory, and machine learning. Despite their shared temporal structure, they differ fundamentally in the nature of their latent states, probabilistic...
Misophonia, characterized by intense negative reactions to specific sounds or related visual cues, remains poorly recognized in clinical settings yet profoundly affects daily life. This study examines how individuals with misophonia experience and sometimes avoid technology that amplifies their triggers. Drawing on 16 semi-structured...
This document, based on feedback from UMR TETIS members and the scientific literature, provides a generic methodology for creating annotation guidelines and annotated textual datasets (corpora). It covers methodological aspects, as well as storage, sharing, and valorization of the data. It includes definitions and examples to clearly...
Large language models are strong sequence predictors, yet standard inference relies on immutable context histories. After making an error at generation step t, the model lacks an updatable memory mechanism that improves predictions for step t+1. We propose LLM-as-RNN, an inference-only framework that turns a frozen LLM into a...
This paper presents CODECO, a federated orchestration framework for Kubernetes that addresses the limitations of cloud-centric deployment. CODECO adopts a data-compute-network co-orchestration approach to support heterogeneous infrastructures, mobility, and multi-provider operation. CODECO extends Kubernetes with semantic...
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...