Expertini Research Research

Browse Research Papers

27,992+ open-access research outputs.

✕ Clear
🔍 vs subrahmanian
Showing 27992 results for "vs subrahmanian"
AI & Data Science Preprint PDF DOI

Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation

Garvin Kruthof · 2026

When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective? We introduce DriftBench, a benchmark for evaluating constraint adherenc…

Read Paper →
AI & Data Science Preprint PDF DOI

FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting

Fengxian Ji, Jingpu Yang, Zirui Song, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen · 2026

Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage, imprecise target-st…

Read Paper →
AI & Data Science Preprint PDF DOI

Differentiable latent structure discovery for interpretable forecasting in clinical time series

Ivan Lerner, Jean Feydy, Alexandre Kalimouttou, Anita Burgun, Francis Bach · 2026

Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpret…

Read Paper →
AI & Data Science Preprint PDF DOI

The Effects of Visual Priming on Cooperative Behavior in Vision-Language Models

Kenneth J. K. Ong · 2026

As Vision-Language Models (VLMs) become increasingly integrated into decision-making systems, it is essential to understand how visual inputs influence their behavior. This paper investigates the effe…

Read Paper →
AI & Data Science Preprint PDF DOI

Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs

Nuria Alabau-Bosque, Jorge Vila-Tomas, Paula Dauden-Oliver, Valero Laparra, Jesus Malo · 2026

Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade perform…

Read Paper →
AI & Data Science Preprint PDF DOI

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering

Xupeng Chen, Binbin Shi, Chenqian Le, Jiaqi Zhang, Kewen Wang, Ran Gong, Jinhan Zhang, Chihang Wang · 2026

Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of …

Read Paper →
AI & Data Science Preprint PDF DOI

Learning Rate Engineering: From Coarse Single Parameter to Layered Evolution

Ming-Hong Yao, Di Wang, Jian Cui, Jin-Yan Chen, Zi-Hao Cui, Fa Wang, Chen Wei, Qiu-Ye Yu · 2026

Learning rate scheduling has evolved from the single global fixed rate of early SGD to sophisticated layer-wise adaptive strategies. We systematize this evolution into five generations: (Gen1) global …

Read Paper →
Computer Science Preprint PDF DOI

The Synthetic Social Graph: Emergent Behavior in AI Agent Communities

Sungguk Cha, DongWook Kim · 2026

Large language model (LLM) agents are increasingly deployed in social settings, yet little is known about how they interact in open-ended environments. We present the first comprehensive sociological …

Read Paper →
AI & Data Science Preprint PDF DOI

When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis

Juergen Dietrich · 2026

Democratic discourse analysis systems increasingly rely on multi-agent LLM pipelines in which distinct evaluator models are assigned adversarial roles to generate structured, multi-perspective assessm…

Read Paper →
Chemistry Preprint PDF DOI

The Great Chicken-and-Egg of Chemistry: Bonding vs. Stability Revisited

Cherif F. Matta · 2026

The chemical bond is a central organizing concept in chemistry, yet it is absent from the molecular Hamiltonian and no "bond operator" exists. Bonding is therefore not a primitive physical entity but …

Read Paper →
Physics Preprint PDF DOI

Six New Variable Stars Discovered from Ground-Based Photometry and Characterized with TESS Data

Maksym Yu. Pyatnytskyy · 2026

We report the discovery of six new variable stars identified through an exploratory analysis of several sky fields observed by the author using a small telescope and a CMOS camera. The search employed…

Read Paper →
AI & Data Science Preprint PDF DOI

TRUST: A Framework for Decentralized AI Service v.0.1

Yu-Chao Huang, Zhen Tan, Mohan Zhang, Pingzhi Li, Zhuo Zhang, Tianlong Chen · 2026

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points …

Read Paper →
Physics Preprint PDF DOI

En Route to a Standard QMA1 vs. QCMA Oracle Separation

David Miloschewsky, Supartha Podder, Dorian Rudolph · 2026

We study the power of quantum witnesses under perfect completeness. We construct a classical oracle relative to which a language lies in $\mathsf{QMA}_1$ but not in $\mathsf{QCMA}$ when the $\mathsf{Q…

Read Paper →
AI & Data Science Preprint PDF DOI

KAYRA: A Microservice Architecture for AI-Assisted Karyotyping with Cloud and On-Premise Deployment

Attila Pinter, Javier Rico, Attila Repai, Jalal Al-Afandi, Adrienn Eva Borsy, Andras Kozma, Hajnalka Andrikovics, Gyorgy Cserey · 2026

We present KAYRA, an end-to-end karyotyping system that operates inside the operational constraints of a clinical cytogenetic laboratory. KAYRA is architected as a containerized microservice pipeline …

Read Paper →
AI & Data Science Preprint PDF DOI

Edge AI for Automotive Vulnerable Road User Safety: Deployable Detection via Knowledge Distillation

Akshay Karjol, Darrin M. Hanna · 2026

Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational constraints. Large models achieve high accuracy but f…

Read Paper →
AI & Data Science Preprint PDF DOI

Random Cloud: Finding Minimal Neural Architectures Without Training

Javier Gil Blazquez · 2026

I propose the \emph{Random Cloud} method, a training-free approach to neural architecture search that discovers minimal feedforward network topologies through stochastic exploration and progressive st…

Read Paper →
Computer Science Preprint PDF DOI

Comparing Smart Contract Paradigms: A Preliminary Study of Security and Developer Experience

Matteo Vaccargiu, Andrea Pinna, Maria Ilaria Lunesu, Giuseppe Destefanis · 2026

Smart contract vulnerabilities have caused billions in financial losses, raising questions about whether programming language paradigms can reduce security overhead. While imperative languages like So…

Read Paper →
Engineering Preprint PDF DOI

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies

Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li · 2026

Skill libraries in deployed robotic systems are continually updated through fine-tuning, fresh demonstrations, or domain adaptation, yet existing typed-composition methods (BLADE, SymSkill, Generative…

Read Paper →
Physics Preprint PDF DOI

Parameterized Quantum Circuits as Feature Maps: Representation Quality and Readout Effects in Multispectral Land-Cover Classification

Ralntion Komini, Aikaterini Mandilara, Georgios Maragkopoulos, Dimitris Syvridis · 2026

We investigate variational quantum classifiers (VQCs) for land-cover classification from multispectral satellite imagery, adopting a feature-map perspective in which the quantum circuit defines a nonl…

Read Paper →
Engineering Preprint PDF DOI

Exploring Converter Control Duality in Microgrids: AC Grid-Forming vs DC Droop Control

Jovan Krajacic, Ognjen Stanojev, Mario Schweizer, Orcun Karaca, Gabriela Hug, Vladan Lazarevic · 2026

Power electronic converters are fundamental building blocks of both AC and DC microgrids, enabling the integration of renewable energy sources, energy storage systems, electronic loads, and electric v…

Read Paper →
Page 1 of 1400 Next →