Isolater - Feed

Ax Shutong Zhang, Dylan Zhou, Yinxiao Liu, Yang Yang, Huiwen Luo, Wenfei Zou 20d ago

Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation

Tool-MCoT framework for content safety moderation using small language models augmented with external tools to reduce computational costs.

Ax W. Russell Neuman 20d ago

The Human Condition as Reflected in Contemporary Large Language Models

Analysis of latent cultural themes in training corpora by prompting six leading LLMs to identify recurring patterns about human culture.

Ax Ryo Nishida, Masayuki Kawarada, Tatsuya Ishigaki, Hiroya Takamura, Masaki Onishi 20d ago

A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction

Study comparing demonstration selection strategies for in-context learning in LLM-based next point-of-interest prediction.

Ax Abdullah Bin Faiz, Arbaz Khan Shehzad, Asad Afzal, Momin Tariq, Muhammad Siddiqi, Muhammad Usamah Shahid, Maryam Noor Awan, Muddassar Farooq 20d ago

Extracting Breast Cancer Phenotypes from Clinical Notes: Comparing LLMs with Classical Ontology Methods

Comparison of LLMs versus classical ontology methods for extracting breast cancer phenotypes from unstructured clinical notes.

Ax Jaehyeok Lee, Xiaoyuan Yi, Jing Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, JinYeong Bak 20d ago

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

DOVE benchmark for evaluating LLM cultural value alignment using open-ended generation rather than multiple-choice formats.

Ax Francesco Sovrano, Alberto Bacchelli 20d ago

Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models

Study on improving faithfulness and traceability in retrieval-augmented generation through illocutionary explanation planning.

Ax Thomas Sounack, Raffaele Giancotti, Catherine A. Gao, Lasai Barre\~nada, Hyeonhoon Lee, Hyung-Chul Lee, Leo Anthony Celi, Karel G. M. Moons, Gary S. Collins, Charlotta Lindvall, Tom Pollard 20d ago

Code Sharing In Prediction Model Research: A Scoping Review

Scoping review quantifying code-sharing practices in prediction model research to inform TRIPOD-Code standards development.

Ax Nandini Arimanda, Achyuth Mukund, Sakthi Balan Muthiah, Rajesh Sharma 20d ago

Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models

Research investigating implicit intersectional biases in LLMs under persona-driven contexts, introducing Bias Amplification framework to capture dynamic bias shifts.

Ax Sadaf Tabatabaee, Sarah S. Lam 20d ago

Unsupervised Neural Network for Automated Classification of Surgical Urgency Levels in Medical Transcriptions

Unsupervised neural network using BioClinicalBERT to automatically classify surgical urgency levels from medical transcriptions.

Ax Khizar Hussain, Bradley A. Malin, Zhijun Yin, Susannah Leigh Rose, Murat Kantarcioglu 20d ago

Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses

Research on detecting hallucinations and omissions in LLM-powered mental health chatbots, finding LLM judges achieve only 52% accuracy on safety-critical healthcare data.

Ax Jared James Grogan 20d ago

The End of the Foundation Model Era: Open-Weight Models, Sovereign AI, and Inference as Infrastructure

ArXiv paper arguing the foundation model era (2020-2025) is ending as open-source models reach frontier performance and inference costs drop, making pre-training non-competitive.

Ax Stella Suge (Executive Director, FilmAid Kenya), Sarah W. Spencer (Senior Researcher, The Distributed AI Research Institute), Nyalleng Moorosi (Senior Researcher, The Distributed AI Research Institute), Helen McElhinney (Executive Director, The CDAC Network), Geoff Loane (Chair, The CDAC Network), Sue Black (Professor of Computer Science,Technology Evangelist, Durham University) 20d ago

From experimentation to engagement: on the paradox of participatory AI and power in contexts of forced displacement and humanitarian crises

Study on participatory AI paradoxes in humanitarian crises and forced displacement contexts.

Ax Meshv Patel, Bikash Baro, Sayan Bayan, Mohendra Roy 20d ago

Development of ML model for triboelectric nanogenerator based sign language detection system

ML and deep learning model comparison for triboelectric sensor-based sign language recognition.

Ax Sambartha Ray Barman, Andrey Starenky, Sophia Bodnar, Nikhil Narasimhan, Ashwin Gopinath 20d ago

The Geometry of Forgetting

Computational model explaining human memory phenomena through high-dimensional geometry without specialized engineering.

Ax Gregory Magarshak 20d ago

Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse

Probabilistic language tries framework unifying compression, decision policies, and execution reuse for sequence models.

Ax Abril Azocar Guzman, Sarath Menon, Tilmann Hickel, Stefan Sandfeld 20d ago

Ontology-based knowledge graph infrastructure for interoperable atomistic simulation data

Ontology-based knowledge graph infrastructure for standardizing atomistic simulation data and provenance.

Ax Wei Zhou, Xuanhe Zhou, Qikang He, Guoliang Li, Bingsheng He, Quanqing Xu, Fan Wu 20d ago

Automating Database-Native Function Code Synthesis with LLMs

LLM-based code synthesis for database-native functions addressing hallucination and domain-specific challenges.

Ax Molly Campbell, Mohamad Sheikho Al Jasem, Ajay Kumar Shrestha 20d ago

Negotiating Privacy with Smart Voice Assistants: Risk-Benefit and Control-Acceptance Tensions

Study on privacy decision-making tensions in smart voice assistants among youth users.

Ax Corby Rosset, Pratyusha Sharma, Andrew Zhao, Miguel Gonzalez-Fernandez, Ahmed Awadallah 20d ago

The Art of Building Verifiers for Computer Use Agents

Framework for building verifiers for computer use agents with principles for constructing rubrics and training signals.

Ax Guy Azov, Ofer Rivlin, Guy Shtar 20d ago

SALLIE: Safeguarding Against Latent Language & Image Exploits

Unified defense mechanism against textual and visual jailbreaks and prompt injections in LLMs and VLMs.

Ax Dikshant Kukreja, Kshitij Sah, Karan Goyal, Mukesh Mohania, Vikram Goyal 20d ago

DISSECT: Diagnosing Where Vision Ends and Language Priors Begin in Scientific VLMs

Study on perception-integration gap in vision-language models: models extract visual info but fail in reasoning.

Ax Gaurav Narasimhan 20d ago

FLeX: Fourier-based Low-rank EXpansion for multilingual transfer

Fourier-based low-rank parameter-efficient fine-tuning for cross-lingual code generation with Code Llama 7B.

Ax Afrah Gueriani, Hamza Kheddar, Ahmed Cherif Mazari, Seref Sagiroglu, Onur Ceran 20d ago

SE-Enhanced ViT and BiLSTM-Based Intrusion Detection for Secure IIoT and IoMT Environments

SE-Enhanced Vision Transformer and BiLSTM hybrid architecture for intrusion detection in IoT/medical environments.

Ax Manuel Ballester, Santiago Lopez-Tapia, Seth Gossage, Patrick Koller, Philipp M. Srivastava, Ugur Demir, Yongseok Jo, Almudena P. Marquez, Christoph Wuersch, Souvik Chakraborty, Vicky Kalogera, Aggelos Katsaggelos 20d ago

Learning the Stellar Structure Equations via Self-supervised Physics-Informed Neural Networks

Physics-informed neural networks for solving stellar structure equations, replacing traditional computational methods with scalable self-supervised learning approach.

Ax Yongzhong Xu 20d ago

Spectral Edge Dynamics Reveal Functional Modes of Learning

Analysis of training dynamics during grokking via spectral edge directions, showing mechanistic interpretability tools miss structured functional modes of learning.

Ax Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Asad Aali, Muhammad Usman Khanzada, Muhammad Usman Rafique, Zihao He, Emily Fox, Dean F. Hougen 20d ago

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

S³: stratified scaling search for test-time inference in diffusion language models using verifier-guided sampling to improve generation quality without retraining.

Ax Chuang Zhao, Hongke Zhao, Xiaofang Zhou, Xiaomeng Li 20d ago

From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning

Dual-stream calibration method for improving contextual clinical reasoning in LLMs through dynamic representation adjustment via in-context learning and RAG.

Ax Jiayuan Liu, Barry Wang, Jiarui Gan, Tonghan Wang, Leon Xie, Mingyu Guo, Vincent Conitzer 20d ago

Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

IAMFM framework optimizing sponsorship configurations in LLM-generated ads using VCG incentives and multi-fidelity optimization under advertiser strategic behavior.

Ax Jueon Park, Wonjune Jang, Chanhwi Kim, Yein Park, Jaewoo Kang 20d ago

ToxReason: A Benchmark for Mechanistic Chemical Toxicity Reasoning via Adverse Outcome Pathway

ToxReason benchmark for evaluating LLM mechanistic reasoning in chemical toxicity prediction via adverse outcome pathways beyond structural features.

Ax Umesh Biswas, Shafqat Hasan, Syed Mohammed Farhan, Nisha Pillai, Charan Gudla 20d ago

Attribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models

Attribution-based explainability for LLM-based intrusion detection in SDN environments, addressing transparency and interpretability in security-critical applications.

Ax Zixuan Chen, Heng Zhang, YuPeng Qin, WenPeng Xing, Qiang Wang, Da Wang, Changting Lin, Meng Han 20d ago

MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE

Multimodal VAE framework for survival risk modeling in multiple myeloma using omics and clinical data with improved latent regularization.

Ax Yehui Yang, Zelin Zang, Changxi Chi, Jingbo Zhou, Xienan Zheng, Yuzhe Jia, Chang Yu, Jinlin Wu, Fuji Yang, Jiebo Luo, Zhen Lei, Stan Z. Li 20d ago

MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation

MAT-Cell: neuro-symbolic multi-agent framework combining LLMs with biological priors for single-cell annotation, addressing generalization and spurious association problems.

Ax Daniil Shafranskyi, Iryna Stopochkina, Mykola Ilin 20d ago

Towards the Development of an LLM-Based Methodology for Automated Security Profiling in Compliance with Ukrainian Cybersecurity Regulations

LLM methodology for automated security profiling in Ukrainian cybersecurity compliance, integrating ISO/IEC 27001 and NIST frameworks.

Ax Ruichen Zhang, Feda AlMuhisen, Chenguang Wan, Zhisong Qu, Kunpeng Li, Youngwoo Cho, Kyungtak Lim, Virginie Grandgirard, Xavier Garbet 20d ago

Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations

Plasma GraphRAG: integrates Graph RAG with LLMs for automated physics-grounded parameter selection in gyrokinetic plasma simulations.

Ax Eleftherios Tzanis, Michail E. Klontzas, Antonios Tzortzakakis 20d ago

DosimeTron: Automating Personalized Monte Carlo Radiation Dosimetry in PET/CT with Agentic AI

DosimeTron: agentic AI system automating personalized Monte Carlo radiation dosimetry in PET/CT with GPT as reasoning engine and 23 specialized tools.

Ax Hongyi Lu, Nian Liu, Shuai Wang, Fengwei Zhang 20d ago

ClawLess: A Security Model of AI Agents

ClawLess: security framework enforcing formally verified policies on autonomous LLM-based AI agents to mitigate code execution and data retrieval risks.

Ax Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi, Antonio Emanuele Cin\`a, Fabio Roli 20d ago

Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization

Hyperbolic geometry-based approach for detecting and sanitizing harmful prompts in Vision-Language Models.

Ax Lin Mu, Haiyang Wang, Li Ni, Lei Sang, Zhize Wu, Peiquan Jin, Yiwen Zhang 20d ago

TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models

TalkLoRA: communication-aware Mixture-of-Experts LoRA framework for parameter-efficient fine-tuning of LLMs with stable expert routing.

Ax Wenyue Hua, Sripad Karne, Qian Xie, Armaan Agrawal, Nikos Pagonas, Kostis Kaffes, Tianyi Peng 20d ago

AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent

AgentOpt v0.1: client-side optimization framework for LLM-based agents composing local tools and remote APIs to reduce latency and costs.

Ax Joy Dutta, Hossien B. Eldeeb, Tu Dac Ho 20d ago

Blockchain and AI: Securing Intelligent Networks for the Future

Overview of blockchain and AI integration for securing IoT, IoH, IoV networks and cyber-physical systems.

Ax Jia-Hong Huang, Seulgi Kim, Yi Chieh Liu, Yixian Shen, Hongyi Zhu, Prayag Tiwari, Stevan Rudinac, Evangelos Kanoulas 20d ago

A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech

Automatic framework for detecting speaker drift in diffusion-based text-to-speech models using binary classification.

Ax Yi Yang, Ovidiu Daescu 20d ago

BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning

Fragment-aware Graph Transformers combining GNNs and Transformers for multi-scale molecular representation learning.

Ax Daniel Otten, Trevor Stalnaker, Nathan Wintersgill, Oscar Chaparro, Denys Poshyvanyk, Douglas Schmidt 20d ago

"Don't Be Afraid, Just Learn": Insights from Industry Practitioners to Prepare Software Engineers in the Age of Generative AI

Survey of 51 industry practitioners on preparing software engineers for generative AI tools, covering hiring and skill gaps.

Ax Ahmed Alansary, Molham Mohamed, Ali Hamdi 20d ago

Severity-Aware Weighted Loss for Arabic Medical Text Generation

Severity-aware weighted loss function for fine-tuning Arabic language models on medical complaint text generation.

Ax Marzi Heidari, Hanping Zhang, Hao Yan, Yuhong Guo 20d ago

Bi-Level Optimization for Single Domain Generalization

Bi-level optimization framework (BiSDG) for single domain generalization without target domain access during training.

Ax Gautham Vinod, Siddeshwar Raghavan, Bruce Coburn, Fengqing Zhu 20d ago

DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images

Vision-language framework for dietary assessment and nutritional analysis from before-and-after food images.

Ax Charlotte Pouw, Hosein Mohebbi, Afra Alishahi, Willem Zuidema 20d ago

In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads

Analyzes in-context learning in speech language models, studying acoustic features, linguistic structure, and induction heads for text-to-speech tasks.

Ax Ziwei Li, Rumali Perera, Angus Forbes, Ken Moreland, Dave Pugmire, Scott Klasky, Wei-Lun Chao, Han-Wei Shen 20d ago