CUEBES

Cognitive networks reconstruct mindsets about STEM subjects and educational contexts in almost 1000 high-schoolers, University students and LLM-based digital twins

arXiv:2602.14749v1 Announce Type: new Abstract: Attitudes toward STEM develop from the interaction of conceptual knowledge, educational experiences, and affect. Here we use cognitive network science...

Mathematics Artificial Intelligence

arXiv CS 1d ago

Depth Completion as Parameter-Efficient Test-Time Adaptation

arXiv:2602.14751v1 Announce Type: new Abstract: We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse...

Software Policy

arXiv CS 1d ago

Measuring the relatedness between scientific publications using controlled vocabularies

arXiv:2602.14755v1 Announce Type: new Abstract: Measuring the relatedness between scientific publications is essential in many areas of bibliometrics and science policy. Controlled vocabularies provide a...

Policy Biology

arXiv CS 1d ago

Solving Inverse Parametrized Problems via Finite Elements and Extreme Learning Networks

arXiv:2602.14757v1 Announce Type: new Abstract: We develop an interpolation-based reduced-order modeling framework for parameter-dependent partial differential equations arising in control, inverse problems, and uncertainty quantification....

Mathematics Software

arXiv CS 1d ago

Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training

arXiv:2602.14759v1 Announce Type: new Abstract: Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often...

Software Policy

arXiv CS 1d ago

Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers

arXiv:2602.14760v1 Announce Type: new Abstract: Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates...

Biology Engineering

arXiv CS 1d ago

Universal Algorithm-Implicit Learning

arXiv:2602.14761v1 Announce Type: new Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current...

Technology Software

arXiv CS 1d ago

Unlocking Reasoning Capability on Machine Translation in Large Language Models

arXiv:2602.14763v1 Announce Type: new Abstract: Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning....

Biology Mathematics

arXiv CS 1d ago

Hierarchical parameter estimation for distributed networked systems: a dynamic consensus approach

arXiv:2602.14765v1 Announce Type: new Abstract: This work introduces a novel two-stage distributed framework to globally estimate constant parameters in a networked system, separating shared information...

Software World News

arXiv CS 1d ago

SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning

arXiv:2602.14767v1 Announce Type: new Abstract: Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting. These...

Psychology Software

arXiv CS 1d ago

On the Parameterized Tractability of Packing Vertex-Disjoint A-Paths with Length Constraints

arXiv:2602.14768v1 Announce Type: new Abstract: Given an undirected graph G and a set A \subseteq V(G), an A-path is a path in G that starts...

Engineering Policy

arXiv CS 1d ago

Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation

arXiv:2602.14770v1 Announce Type: new Abstract: Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized...

Policy Artificial Intelligence

arXiv CS 1d ago

GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture

arXiv:2602.14771v1 Announce Type: new Abstract: The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes,...

Environment Psychology

arXiv CS 1d ago

Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks

arXiv:2602.14772v1 Announce Type: new Abstract: The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat...

Artificial Intelligence Neuroscience

arXiv CS 1d ago

Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment

arXiv:2602.14777v1 Announce Type: new Abstract: Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon...

Artificial Intelligence Psychology

arXiv CS 1d ago

A Geometric Analysis of Small-sized Language Model Hallucinations

arXiv:2602.14778v1 Announce Type: new Abstract: Hallucinations -- fluent but factually incorrect responses -- pose a major challenge to the reliability of language models, especially in...

Policy Artificial Intelligence

arXiv CS 1d ago

ROSA: Roundabout Optimized Speed Advisory with Multi-Agent Trajectory Prediction in Multimodal Traffic

arXiv:2602.14780v1 Announce Type: new Abstract: We present ROSA -- Roundabout Optimized Speed Advisory -- a system that combines multi-agent trajectory prediction with coordinated speed guidance...

Software Policy

arXiv CS 1d ago

What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation

arXiv:2602.14783v1 Announce Type: new Abstract: The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders,...

Software Cybersecurity

arXiv CS 1d ago

Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs

arXiv:2602.14784v1 Announce Type: new Abstract: Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or...

Software Technology

arXiv CS 1d ago

New Randomized Global Generalized Minimum Residual (RGl-GMRES) method

arXiv:2602.14786v1 Announce Type: new Abstract: In this paper, we develop a new Randomized Global Generalized Minimum Residual (RGlGMRES) algorithm for efficiently computing solutions to large...

Software World News

arXiv CS 1d ago

VIPA: Visual Informative Part Attention for Referring Image Segmentation

arXiv:2602.14788v1 Announce Type: new Abstract: Referring Image Segmentation (RIS) aims to segment a target object described by a natural language expression. Existing methods have evolved...

Engineering Software

arXiv CS 1d ago

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials

arXiv:2602.14789v1 Announce Type: new Abstract: The dynamical stability of the iterates during training plays a key role in determining the minima obtained by optimization algorithms....

Psychology Policy

arXiv CS 1d ago

Extending Multi-Source Bayesian Optimization With Causality Principles

arXiv:2602.14791v1 Announce Type: new Abstract: Multi-Source Bayesian Optimization (MSBO) serves as a variant of the traditional Bayesian Optimization (BO) framework applicable to situations involving optimization...

Policy Software

arXiv CS 1d ago

Beyond Retractions: Forensic Scientometrics Techniques to Identify Research Misconduct, Citation Leakage, and Funding Anomalies

arXiv:2602.14793v1 Announce Type: new Abstract: This paper presents a forensic scientometric case study of the Pharmakon Neuroscience Research Network, a fabricated research collective that operated...

Publishing Technology