arXivLabs
PulseAugur coverage of arXivLabs — every cluster mentioning arXivLabs across labs, papers, and developer communities, ranked by signal.
23 day(s) with sentiment data
-
Machine learning framework estimates pedestrian volumes using GIS data
Researchers have developed a machine learning framework to estimate pedestrian volumes using GIS data, aiming to improve safety investment prioritization for transportation agencies. The proposed pipeline, which include…
-
New theory unifies AI communication, control, and decision-making
A new paper proposes a mathematical framework for pragmatic information theory, aiming to unify communication, control, and decision-making. The theory introduces the concept of isoteleia, which formalizes the idea that…
-
New Benchmark Tests AI Agents on Complex, Multimodal Long-Horizon Research
Researchers have introduced Mr.LHDR, a new benchmark designed to evaluate deep research agents on their ability to handle long, complex, and multimodal research tasks. The benchmark features questions requiring an avera…
-
Quantum Reservoir Computing Achieves Molecular Property Prediction Breakthrough
Researchers have developed a novel quantum reservoir computing architecture using discrete time crystals (DTCs) to predict molecular properties. This DTC-based system processes local molecular graph events and surface-h…
-
New deep learning framework predicts drug effects from single-cell data
Researchers have developed scDEFT, a novel deep learning framework designed to predict drug effects and enable counterfactual reasoning using single-cell data. This framework treats drugs as conditioning operators on ce…
-
New 3D Deep Learning Framework Enhances Brain Metastasis Detection in MRI
Researchers have developed a novel scale-aware 3D deep learning framework to improve the detection of brain metastases in multimodal MRI scans. This method combines the outputs of independently trained 3D U-Nets with di…
-
New method improves LLM graph captioning with motif-based translation
Researchers have developed a new method called Structurally Speaking to improve graph captioning using large language models like GPT-5.1. This protocol guides the translation between explicit graph connectivity and con…
-
New algorithm enables safe learning in irreversible environments
Researchers have developed a novel learning algorithm designed for agents operating in environments with irreversible dynamics, where mistakes cannot be undone. This algorithm allows agents to request assistance from a …
-
New framework models security assurance under resource constraints
A new research paper introduces a theoretical framework for evaluating security assurance under resource constraints. The framework distinguishes between repeated success, unique coverage, accepted evidence, and operati…
-
New math paper details nonlocal transport convergence rates
A new paper published on arXiv details a mathematical framework for understanding nonlocal transport phenomena. The research focuses on the convergence of solutions to a nonlocal continuity equation towards heat flow, e…
-
New automated pipeline enhances camera intrinsic calibration for robots
Researchers have developed an automated pipeline for camera intrinsic calibration, a crucial step for accurate robot perception. This new method automatically filters high-quality images and determines the appropriate r…
-
AI literacy framework proposed to boost sustainable development goals
A new study published on arXiv proposes a framework for integrating AI literacy into sustainable development initiatives. The research introduces a six-level taxonomy of artificial intelligence reasoning and ethics, aim…
-
New Frank-Wolfe algorithms target convex function minimization with sparsity
Researchers have developed new accelerated first-order algorithms within the Frank-Wolfe (FW) family designed for minimizing smooth convex functions. These algorithms are particularly focused on two constraint classes: …
-
Study: LLMs shift peer reviewer preference away from lexical complexity
A new study published on arXiv investigates how peer reviewers' preferences for lexical complexity in academic papers have shifted over time, particularly in the context of the rise of large language models. By using a …
-
New framework tackles pricing and inventory with contextual, censored demand
Researchers have developed a new framework to address the challenge of optimal pricing and inventory control for retailers facing fluctuating market conditions and obscured demand data. The proposed model treats demand …
-
New Arena Connects LLM Red-Team Attacks and Blue-Team Defenses
Researchers have developed ACEA, an Adversarial Co-Evolution Arena designed to test large language models (LLMs) by pitting red-team attacks against blue-team defenses in a head-to-head format. This platform connects va…
-
Robots infer human goals by guiding them to critical decision points
Researchers have developed a novel strategy to enable robots to infer human goals more accurately and earlier during interactions. This approach focuses on guiding humans toward "Critical Decision Points" (CDPs), which …
-
New World Model Approach Handles Asynchronous Sensor Data
Researchers have developed a new approach for world models that can handle asynchronous sensor observations, a common challenge in physical systems where sensors operate at different rates. The proposed method involves …
-
AI Safety Research: Generator-Independent Runtime Assurance Proposed
A new research paper proposes a method for generator-independent runtime assurance under partial observation in artificial intelligence systems. The work introduces the concept of simultaneous setwise soundness, which i…
-
New AI methods tackle business process planning under uncertainty
Researchers have developed new methods for planning and scheduling business processes that account for uncertainty in control flow. The proposed approaches aim to improve efficiency by reducing makespan and minimizing s…