GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks
arXiv:2512.22207v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) are proficient in perception and instruction-following, but they still struggle with spatial reasoning: the ability to mentally track and manipulate objects across multiple views and over time. Spatial reasonin...
Toward Equitable Recovery: A Fairness-Aware AI Framework for Prioritizing Post-Flood Aid in Bangladesh
arXiv:2512.22210v1 Announce Type: new
Abstract: Post-disaster aid allocation in developing nations often suffers from systematic biases that disadvantage vulnerable regions, perpetuating historical inequities. This paper presents a fairness-aware artificial intelligence framework for prioritizing p...
With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems
arXiv:2512.22211v1 Announce Type: new
Abstract: Agentic AI systems present both significant opportunities and novel risks due to their capacity for autonomous action, encompassing tasks such as code execution, internet interaction, and file modification. This poses considerable challenges for effec...
Physics-Informed Neural Solvers for Periodic Quantum Eigenproblems
arXiv:2512.21349v1 Announce Type: new
Abstract: This thesis presents a physics-informed machine learning framework for solving the Floquet-Bloch eigenvalue problem associated with particles in two-dimensional periodic potentials, with a focus on honeycomb lattice geometry, due to its distinctive ba...
A Reinforcement Learning Approach to Synthetic Data Generation
arXiv:2512.21395v1 Announce Type: new
Abstract: Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet, state-of-the-art generative models often require large datasets and complex training procedures, limiting th...
kooplearn: A Scikit-Learn Compatible Library of Algorithms for Evolution Operator Learning
arXiv:2512.21409v1 Announce Type: new
Abstract: kooplearn is a machine-learning library that implements linear, kernel, and deep-learning estimators of dynamical operators and their spectral decompositions. kooplearn can model both discrete-time evolution operators (Koopman/Transfer) and continuous...
DeepCQ: General-Purpose Deep-Surrogate Framework for Lossy Compression Quality Prediction
arXiv:2512.21433v1 Announce Type: new
Abstract: Error-bounded lossy compression techniques have become vital for scientific data management and analytics, given the ever-increasing volume of data generated by modern scientific simulations and instruments. Nevertheless, assessing data quality post-c...
From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration
arXiv:2512.21360v1 Announce Type: new
Abstract: Background: The House-Tree-Person (HTP) drawing test, introduced by John Buck in 1948, remains a widely used projective technique in clinical psychology. However, it has long faced challenges such as heterogeneous scoring standards, reliance on examin...
Three-way conflict analysis based on alliance and conflict functions
arXiv:2512.21419v1 Announce Type: new
Abstract: Trisecting agents, issues, and agent pairs are essential topics of three-way conflict analysis. They have been commonly studied based on either a rating or an auxiliary function. A rating function defines the positive, negative, or neutral ratings of ...
Feasible strategies in three-way conflict analysis with three-valued ratings
arXiv:2512.21420v1 Announce Type: new
Abstract: Most existing work on three-way conflict analysis has focused on trisecting agent pairs, agents, or issues, which contributes to understanding the nature of conflicts but falls short in addressing their resolution. Specifically, the formulation of fea...
Eating more vitamin C can physically change your skin
Vitamin C doesn’t just belong in skincare products—it works even better when you eat it. Scientists discovered that vitamin C from food travels through the bloodstream into every layer of the skin, boosting collagen and skin renewal. People who ate two vitamin C–packed kiwifruit daily showed thicker...
Parameter-Efficient Neural CDEs via Implicit Function Jacobians
arXiv:2512.20625v1 Announce Type: new
Abstract: Neural Controlled Differential Equations (Neural CDEs, NCDEs) are a unique branch of methods, specifically tailored for analysing temporal sequences. However, they come with drawbacks, the main one being the number of parameters, required for the meth...
Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning
arXiv:2512.20629v1 Announce Type: new
Abstract: This study proposes a multi-agent language framework that enables continual strategy evolution without fine-tuning the language model's parameters. The core idea is to liberate the latent vectors of abstract concepts from traditional static semantic r...
Zero-Training Temporal Drift Detection for Transformer Sentiment Models: A Comprehensive Analysis on Authentic Social Media Streams
arXiv:2512.20631v1 Announce Type: new
Abstract: We present a comprehensive zero-training temporal drift analysis of transformer-based sentiment models validated on authentic social media data from major real-world events. Through systematic evaluation across three transformer architectures and rigo...
Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
arXiv:2512.20634v1 Announce Type: new
Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than true knowledge...
BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization
arXiv:2512.20623v1 Announce Type: new
Abstract: Smart home lighting systems consume 15-20% of residential energy but lack adaptive intelligence to optimize for user comfort and energy efficiency simultaneously. We present BitRL-Light, a novel framework combining 1-bit quantized Large Language Model...
Quantum-Inspired Multi Agent Reinforcement Learning for Exploration Exploitation Optimization in UAV-Assisted 6G Network Deployment
arXiv:2512.20624v1 Announce Type: new
Abstract: This study introduces a quantum inspired framework for optimizing the exploration exploitation tradeoff in multiagent reinforcement learning, applied to UAVassisted 6G network deployment. We consider a cooperative scenario where ten intelligent UAVs a...
arXiv:2512.20626v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to dynamically access external information, which is powerful for answering questions over previously unseen documents. Nonetheless, they struggle with high-level conceptual und...
MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
arXiv:2512.20630v1 Announce Type: new
Abstract: Foundation model reliability assessment typically requires thousands of evaluation examples, making it computationally expensive and time-consuming for real-world deployment. We introduce microprobe, a novel approach that achieves comprehensive reliab...
Large Language Models for EDA Cloud Job Resource and Lifetime Prediction
arXiv:2512.19701v1 Announce Type: new
Abstract: The rapid growth of cloud computing in the Electronic Design Automation (EDA) industry has created a critical need for resource and job lifetime prediction to achieve optimal scheduling. Traditional machine learning methods often struggle with the com...
Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches
arXiv:2512.19713v1 Announce Type: new
Abstract: Human activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements. While fully supervised techniques achieve high accuracy, they...
Development and external validation of a multimodal artificial intelligence mortality prediction model of critically ill patients using multicenter data
arXiv:2512.19716v1 Announce Type: new
Abstract: Early prediction of in-hospital mortality in critically ill patients can aid clinicians in optimizing treatment. The objective was to develop a multimodal deep learning model, using structured and unstructured clinical data, to predict in-hospital mor...
Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference
arXiv:2512.19717v1 Announce Type: new
Abstract: Finding rare but useful solutions in very large candidate spaces is a recurring practical challenge across language generation, planning, and reinforcement learning. We present a practical framework, \emph{Inverted Causality Focusing Algorithm} (ICFA)...