CUEBES

Demographic Probing of Large Language Models Lacks Construct Validity

arXiv:2601.18486v1 Announce Type: new Abstract: Demographic probing is widely used to study how large language models (LLMs) adapt their behavior to signaled demographic attributes. This...

Software Artificial Intelligence

arXiv CS Jan 28

DV-VLN: Dual Verification for Reliable LLM-Based Vision-and-Language Navigation

arXiv:2601.18492v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) requires an embodied agent to navigate in a complex 3D environment according to natural language instructions. Recent...

Software Artificial Intelligence

arXiv CS Jan 28

DisasterInsight: A Multimodal Benchmark for Function-Aware and Grounded Disaster Assessment

arXiv:2601.18493v1 Announce Type: new Abstract: Timely interpretation of satellite imagery is critical for disaster response, yet existing vision-language benchmarks for remote sensing largely focus on...

Software Biology

arXiv CS Jan 28

Real-Time Prediction of Lower Limb Joint Kinematics, Kinetics, and Ground Reaction Force using Wearable Sensors and Machine Learning

arXiv:2601.18494v1 Announce Type: new Abstract: Walking is a key movement of interest in biomechanics, yet gold-standard data collection methods are time- and cost-expensive. This paper...

Artificial Intelligence Software

arXiv CS Jan 28

DEEPMED: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference

arXiv:2601.18496v1 Announce Type: new Abstract: Medical reasoning models remain constrained by parametric knowledge and are thus susceptible to forgetting and hallucinations. DeepResearch (DR) models ground...

Medicine & Health Chemistry

arXiv CS Jan 28

BAIT: Visual-illusion-inspired Privacy Preservation for Mobile Data Visualization

arXiv:2601.18497v1 Announce Type: new Abstract: With the prevalence of mobile data visualizations, there have been growing concerns about their privacy risks, especially shoulder surfing attacks....

Software Cybersecurity

arXiv CS Jan 28

Regulatory Hub Discovery in MDD Methylome: Hypotheses for Molecular Subtypes via Computational Analysis

arXiv:2601.18498v1 Announce Type: new Abstract: Major Depressive Disorder (MDD) is a clinically heterogeneous syndrome with diverse etiological pathways. Traditional Epigenome-Wide Association Studies (EWAS) have successfully...

Genetics Biology

arXiv CS Jan 28

Nearly Optimal Bayesian Inference for Structural Missingness

arXiv:2601.18500v2 Announce Type: new Abstract: Structural missingness breaks 'just impute and train': values can be undefined by causal or logical constraints, and the mask may...

Engineering

arXiv CS Jan 28

Pointwise-in-time convergence analysis of an Alikhanov scheme for a 2D nonlinear subdiffusion equation

arXiv:2601.18505v1 Announce Type: new Abstract: In this paper, we discretize the Caputo time derivative of order \alpha \in (0,1) using the Alikhanov scheme on a...

Software Energy

arXiv CS Jan 28

Conformal Prediction Algorithms for Time Series Forecasting: Methods and Benchmark

arXiv:2601.18509v1 Announce Type: new Abstract: Reliable uncertainty quantification is of critical importance in time series forecasting, yet traditional methods often rely on restrictive distributional assumptions....

Software Artificial Intelligence

arXiv CS Jan 28

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates

arXiv:2601.18510v1 Announce Type: new Abstract: While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen...

Software Artificial Intelligence

arXiv CS Jan 28

Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B

arXiv:2601.18511v1 Announce Type: new Abstract: As large language models (LLMs) become ubiquitous, privacy concerns pertaining to inference inputs keep growing. In this context, fully homomorphic...

Artificial Intelligence Cybersecurity

arXiv CS Jan 28

Using Large Language Models to Construct Virtual Top Managers: A Method for Organizational Research

arXiv:2601.18512v1 Announce Type: new Abstract: This study introduces a methodological framework that uses large language models to create virtual personas of real top managers. Drawing...

Software Artificial Intelligence

arXiv CS Jan 28

LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models

arXiv:2601.18513v1 Announce Type: new Abstract: Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance....

Technology Biology

arXiv CS Jan 28

Ribbons from Independence Structure: Hypercontractivity, $\Phi$-Mutual Information, and Matrix $\Phi$-Entropy

arXiv:2601.18516v1 Announce Type: new Abstract: We study the hypercontractivity ribbon and the $\Phi$-ribbon for joint distributions that obey a given independence structure, obtaining tight bounds...

Biology

arXiv CS Jan 28

GenAI for Social Work Field Education: Client Simulation with Real-Time Feedback

arXiv:2601.18517v1 Announce Type: new Abstract: Field education is the signature pedagogy of social work, yet providing timely and objective feedback during training is constrained by...

Neuroscience Software

arXiv CS Jan 28

A BFBt preconditioner for Double Saddle-Point Systems

arXiv:2601.18520v1 Announce Type: new Abstract: We consider block preconditioners for double saddle-point systems, and investigate the effect of approximating the nested Schur complement associated with...

Software Biology

arXiv CS Jan 28

Scalable Transit Delay Prediction at City Scale: A Systematic Approach with Multi-Resolution Feature Engineering and Deep Learning

arXiv:2601.18521v1 Announce Type: new Abstract: Urban bus transit agencies need reliable, network-wide delay predictions to provide accurate arrival information to passengers and support real-time operational...

Engineering Biology

arXiv CS Jan 28

From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at Scale

arXiv:2601.18524v1 Announce Type: new Abstract: Accurate prediction of nuclear magnetic resonance (NMR) chemical shifts is fundamental to spectral analysis and molecular structure elucidation, yet existing...

Artificial Intelligence Genetics

arXiv CS Jan 28

Closing the Modality Gap Aligns Group-Wise Semantics

arXiv:2601.18525v1 Announce Type: new Abstract: In multimodal learning, CLIP has been recognized as the \textit{de facto} method for learning a shared latent space across multiple...

Engineering Biology

arXiv CS Jan 28

Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models

arXiv:2601.18527v1 Announce Type: new Abstract: With context windows of millions of tokens, Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative...

Software Biology

arXiv CS Jan 28

From Cold Start to Active Learning: Embedding-Based Scan Selection for Medical Image Segmentation

arXiv:2601.18532v1 Announce Type: new Abstract: Accurate segmentation annotations are critical for disease monitoring, yet manual labeling remains a major bottleneck due to the time and...

Medicine & Health Software

arXiv CS Jan 28

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

arXiv:2601.18533v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer...

Software Cybersecurity

arXiv CS Jan 28

Evaluating Morphological Plausibility of Subword Tokenization via Statistical Alignment with Morpho-Syntactic Features

arXiv:2601.18536v1 Announce Type: new Abstract: We present a novel metric for the evaluation of the morphological plausibility of subword segmentation. Unlike the typically used morpheme...

Software