Isolater - Feed

Ax Wilson E. Marc\'ilio-Jr, Danilo M. Eler 3/26/2026

Navigating the Concept Space of Language Models

ConceptMap tool enables scalable exploratory discovery of human-interpretable concepts in sparse autoencoders trained on LLM activations.

Ax Reuben Chagas Fernandes, Gaurang S. Patkar 3/26/2026

Konkani LLM: Multi-Script Instruction Tuning and Evaluation for a Low-Resource Indian Language

Konkani-Instruct-100k synthetic dataset and benchmarks address LLM performance gaps for low-resource Indian language across multiple scripts via instruction tuning.

Ax Avni Mittal 3/26/2026

Did You Forget What I Asked? Prospective Memory Failures in Large Language Models

Cognitive psychology-inspired study reveals LLMs drop formatting instruction compliance by 2-21% under concurrent task load, identifying prospective memory vulnerabilities.

Ax Satya Sri Rajiteswari Nimmagadda, Ethan Young, Niladri Sengupta, Ananya Jana, Aniruddha Maiti 3/26/2026

Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs

Fine-tuned lightweight LLM generates hierarchical JSON representations of scientific sentences preserving semantic meaning for structured knowledge extraction.

Ax Bhavik Mangla 3/26/2026

MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG

MDKeyChunker pipeline enables structure-aware chunking of Markdown documents and single-call LLM enrichment with metadata extraction for improved RAG accuracy.

Ax Harry Collins, Simon Thorne 3/26/2026

Large Language Models and Scientific Discourse: Where's the Intelligence?

Philosophical comparison of how LLMs gather data versus human scientific knowledge construction and discovery processes.

Ax Yukun Wu, Lihui Liu 3/26/2026

Mixture of Demonstrations for Textual Graph Understanding and Question Answering

Mixture of Demonstrations approach improves GraphRAG performance for domain-specific QA by selecting high-quality demonstrations to reduce irrelevant retrieved information.

Ax Tuan-Anh Vu, S\'ebastien Destercke, Fr\'ed\'eric Pichon 3/26/2026

Upper Entropy for 2-Monotone Lower Probabilities

Computational analysis of upper entropy algorithms for uncertainty quantification in credal set-based probability models.

Ax Yuxi Chen, Haoyu Zhai, Chenkai Wang, Rui Yang, Lingming Zhang, Gang Wang, Huan Zhang 3/26/2026

CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training

Native GUI agent framework ReCAP adds CAPTCHA-solving capability to vision-language models using self-corrective training and automated reasoning-action data generation.

Ax Seungju Han, Konwoo Kim, Chanwoo Park, Benjamin Newman, Suhas Kotha, Jaehun Jung, James Zou, Yejin Choi 3/26/2026

Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG

Synthetic Mixed Training combines synthetic QAs and documents to improve LLM knowledge acquisition beyond RAG performance in data-constrained domains.

Ax Chenglin Li, Guangchun Ruan, Hua Geng 3/26/2026

Safe Reinforcement Learning with Preference-based Constraint Inference

Safe reinforcement learning approach using preference-based constraint inference for learning complex, subjective safety constraints with minimal expert demonstrations.

Ax Jiehao Wu, Zixiao Huang, Wenhao Li, Chuyun Shen, Junjie Sheng, Xiangfeng Wang 3/26/2026

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization

AI agent optimizes operator performance on Huawei Ascend NPUs by addressing knowledge bottleneck through episodic learning for tiling and kernel programs.

Ax Zhiyuan Chen, Yuxuan Zhong, Fan Wang, Bo Yu, Pengtao Shao, Shaoshan Liu, Ning Ding 3/26/2026

StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation

StateLinFormer: linear-attention navigation model with persistent memory for long-term navigation tasks, combining flexibility with efficiency.

Ax Gaspard Abel, Eloi Campagne, Mohamed Benloughmari, Argyris Kalogeratos 3/26/2026

Dual-Criterion Curriculum Learning: Application to Temporal Data

Dual-Criterion Curriculum Learning proposes a meta-learning approach using dual criteria for difficulty assessment in temporal data training.

Ax Tao Liu, Jiguang Lv, Dapeng Man, Weiye Xi, Yaole Li, Feiyu Zhao, Kuiming Wang, Yingchao Bian, Chen Xu, Wu Yang 3/26/2026

PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning

PoiCGAN introduces poisoning attack methods against federated learning systems using feature-label joint perturbation.

Ax Meriem Bouzouad, Yuan-Hao Chang, Jalil Boukhobza 3/26/2026

APreQEL: Adaptive Mixed Precision Quantization For Edge LLMs

APreQEL proposes adaptive mixed precision quantization to reduce memory and computational costs of LLMs for edge device deployment while maintaining performance.

Ax Hyunwoo Kim, Munyoung Lee, Seung Hyub Jeon, Kyu Sung Lee 3/26/2026

Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM

Time-LLM model for predicting wafer-level spatial etch depth distributions in plasma etching process monitoring.

Ax Saswata Bose, Suvadeep Maiti, Shivam Kumar Sharma, Mythirayee S, Tapabrata Chakraborti, Srijitesh Rajendran, Raju S. Bapi 3/26/2026

AI Generalisation Gap In Comorbid Sleep Disorder Staging

Analysis of deep learning generalization gap in sleep disorder staging with Grad-CAM interpretability and iSLEEPS clinical dataset.

Ax Steven Cho, Stefano Ruberto, Valerio Terragni 3/26/2026

LLMORPH: Automated Metamorphic Testing of Large Language Models

LLMORPH automated testing tool for LLMs using metamorphic testing to detect NLP task failures without human-labeled oracles.

Ax Ravin Ravi, Dylan Bradshaw, Stefano Ruberto, Gunel Jahangirova, Valerio Terragni 3/26/2026

LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops

LLMLOOP framework automating iterative refinement of LLM-generated code and test cases through automated feedback loops.

Ax Zhuo-Yang Song, Hua Xing Zhu 3/26/2026

A Theory of LLM Information Susceptibility

Theory of LLM information susceptibility analyzing fundamental limits of LLM-mediated optimization in agentic systems.

Ax Yurii Laba, Yaryna Mohytych, Ivanna Rohulia, Halyna Kyryleyza, Hanna Dydyk-Meush, Oles Dobosevych, Rostyslav Hryniv 3/26/2026

Ukrainian Visual Word Sense Disambiguation Benchmark

Ukrainian Visual Word Sense Disambiguation benchmark with 10-image choices for evaluating word sense disambiguation in Ukrainian.

Ax Fatih Uenal 3/26/2026

Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks

Swiss-Bench SBP-002: trilingual benchmark of 395 expert-crafted regulatory compliance tasks across FINMA, Legal-CH, and EFK domains.

Ax Federico Carrara, Talley Lambert, Mehdi Seifi, Florian Jug 3/26/2026

{\lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy

Self-supervised learning method for spectral unmixing in fluorescence microscopy using data-driven approach.

Ax Weilun Xu, Alexander Rusnak, Frederic Kaplan 3/26/2026

Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges

Probing study revealing how LLMs internally represent different ethical frameworks with asymmetric transfer patterns across model sizes.

Ax Octavian Pascu, Dan Oneata, Horia Cucu, Nicolas M. Muller 3/26/2026

Echoes: A semantically-aligned music deepfake detection dataset

Echoes dataset with 3,577 music tracks for deepfake detection spanning multiple AI music generation systems.

Ax Jannik Endres, Etienne Lalibert\'e, David Rolnick, Arthur Ouaknine 3/26/2026

Estimating Individual Tree Height and Species from UAV Imagery

BIRCH-Trees benchmark for estimating individual tree height and species from RGB UAV imagery for forest monitoring.

Ax Shreen Gul, Mohamed Elmahallawy, Ardhendu Tripathy, Sanjay Madria 3/26/2026

Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection

Training-free out-of-distribution detection using multi-layer prototype fusion approach for robust deep learning deployment.

Ax Manjushree B. Aithal, Ph. D., Alexander Kotz, James Mitchell, Ph. D 3/26/2026

PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation

Privacy-preserving LLM system for disambiguating clinical acronyms in healthcare without transmitting data to external servers.

Ax Nur Afsa Syeda, Mohamed Elmahallawy, Luis Fernando de la Torre, John Miller 3/26/2026

Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvesting

Machine learning approach for robotic fruit harvesting using active reachability estimation to improve efficiency in unstructured environments.

Ax Licol Zeinfeld, Alona Strugatski, Ziva Bar-Dov, Ron Blonder, Shelley Rap, Giora Alexandron 3/26/2026

Assessment Design in the AI Era: A Method for Identifying Items Functioning Differentially for Humans and Chatbots

Measurement methodology for identifying assessment items where LLMs perform differently than humans using theory-grounded evaluation.

Ax Rui Wei, Rui Du, Hanfei Yu, Devesh Tiwari, Jian Li, Zhaozhuo Xu, Hao Wang 3/26/2026

The Diminishing Returns of Early-Exit Decoding in Modern LLMs

Analysis of early-exit decoding in modern LLMs showing reduced efficiency gains due to improved architectures with lower layer redundancy.

Ax Duo Lu, Helena Caminal, Manos Chatzakis, Yannis Papakonstantinou, Yannis Chronis, Vaibhav Jain, Fatma \"Ozcan 3/26/2026

An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments and Analysis]

Study of filtered vector search algorithms in PostgreSQL for semantic search and GenAI applications, evaluating real-world database performance.

Ax Shaonan Liu, Yuichiro Iwashita, Soichiro Nakako, Masakazu Iwamura, Koichi Kise 3/26/2026

CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records

Continuous-time diffusion models for generating synthetic electronic health records with mixed numerical and categorical features.

Ax Mohsen Sahraei Ardakani, Rui Song 3/26/2026

Self Paced Gaussian Contextual Reinforcement Learning

Self-paced curriculum learning for RL using closed-form Gaussian updates to improve efficiency in high-dimensional contexts.

Ax Md. Kamrul Hossain, Walid Aljoby 3/26/2026

AI-driven Intent-Based Networking Approach for Self-configuration of Next Generation Networks

Intent-Based Networking using AI to translate high-level natural language intents into network policies with automated compliance assurance.

Ax Harun Tolasa, Volkan Patoglu 3/26/2026

Human-in-the-Loop Pareto Optimization: Trade-off Characterization for Assist-as-Needed Training and Performance Evaluation

Human-in-the-loop Pareto optimization for motor skill training and rehabilitation, characterizing task difficulty vs. performance trade-offs.

Ax Kuepon Aueawatthanaphisut, Kuepon Aueawatthanaphisut 3/26/2026