Isolater - Feed

Ax Jaechang Kim, Yotaro Shimose, Zhao Wang, Kuang-Da Wang, Jungseul Ok, Shingo Takamatsu 3/18/2026

Visual Prompt Discovery via Semantic Exploration

Visual prompt discovery method to diagnose and mitigate LVLM perception failures through semantic exploration.

Ax Junxin Wang, Dai Guan, Weijie Qiu, Zhihang Li, Yongbo Gai, Zhengyi Yang, Mengyu Zhou, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang 3/18/2026

Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models

Vision-language process reward models with explicit visual premise verification for reliable step scoring in reasoning.

Ax Yuan Tian, Yi Mei, Mengjie Zhang 3/18/2026

Surrogate-Assisted Genetic Programming with Rank-Based Phenotypic Characterisation for Dynamic Multi-Mode Project Scheduling

Genetic programming with surrogate models for dynamic multi-mode project scheduling with simulation-based optimization.

Ax Zhengbo Zhang, Jinbo Su, Zhaowen Zhou, Changtao Miao, Yuhan Hong, Qimeng Wu, Yumeng Liu, Feier Wu, Yihe Tian, Yuhao Liang, Zitong Shan, Wanke Xia, Yi-Fan Zhang, Bo Zhang, Zhe Li, Shiming Xiang, Ying Yan 3/18/2026

VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agents

VisBrowse-Bench benchmark for evaluating visual-native search in multimodal browsing agents using MLLMs.

Ax Ke Yang, Bolin Chen, Yuejie Li, Yueying Hua, Jianhao Nie, Yueping He, Bowen Li, Chengjun Mao 3/18/2026

Attention-guided Evidence Grounding for Spoken Question Answering

End-to-end framework using Speech LLMs for spoken question answering with attention-guided evidence grounding.

Ax Marcos Galdino, Johanna Grahl, Tobias Hamann, Anas Abdelrazeq, Ingrid Isenhardt 3/18/2026

A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems

Human-centered architecture for integrating LLM-based cognitive assistants into manufacturing quality management systems.

Ax Isha Andrade, Shalaka S Mahadik, Mithun Mukherjee, Pranav M Pawar, Raja Muthalagu 3/18/2026

Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models

Security research on sentiment steering attacks targeting RAG-enabled large language models and LLM robustness.

Ax S. Yatawatta, A. Ahmadi, B. Asabere, M. Iacobelli, N. Peters, M. Veldhuis 3/18/2026

Explainable machine learning workflows for radio astronomical data processing

Machine learning pipelines for radio astronomy data processing with explainability focus on automating configuration.

Ax Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Alvaro Doria Dos Santos, Luciana Bueno Dos Reis Fernandes, Ricardo V. Godoy, Eduardo A. B. Almeida, Helena Carolina Onody, Marcelo Andrade Da Costa Vieira, Angelica Maria Penteado-Dias, Marcelo Becker 3/18/2026

Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI

YOLO-based deep learning for automated wasp identification with explainable AI integration for taxonomic classification.

Ax Yong Il Choi 3/18/2026

DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity

DynamicGate MLP conditional computation framework using learned structural dropout and input-dependent gating for efficiency.

Ax Andrea Moleri, Christian Intern\`o, Ali Raza, Markus Olhofer, David Klindt, Fabio Stella, Barbara Hammer 3/18/2026

FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios

FederatedFactory zero-dependency framework for federated learning in non-IID scenarios using generative one-shot learning.

Ax Jishen Peng, Enze Jiang, Zheng Ma, Xiongbin Yan 3/18/2026

Robust Physics-Guided Diffusion for Full-Waveform Inversion

Physics-guided diffusion framework for full-waveform inversion combining score-based generative models with wave-equation simulations.

Ax FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad, Minhaj Ahmad, Abdulaziz Al-Homaid, Anas Al-Nuaimi, Enes Altinisik, Ehsaneddin Asgari, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Asim Ersoy, Masoomali Fatehkia, Mohammed Qusay Hashim, Majd Hawasly, Mohamed Hefeeda, Mus'ab Husaini, Keivin Isufaj, Soon-Gyo Jung, Houssam Lachemat, Ji Kim Lucas, Abubakr Mohamed, Tasnim Mohiuddin, Basel Mousi, Hamdy Mubarak, Ahmad Musleh, Mourad Ouzzani, Amin Sadeghi, Husrev Taha Sencar, Mohammed Shinoy, Omar Sinan, Yifan Zhang 3/18/2026

Fanar 2.0: Arabic Generative AI Stack

Fanar 2.0 Arabic generative AI platform built on 256 H100 GPUs at QCRI with sovereign infrastructure and data pipelines.

Ax Finnur \'Ag\'ust Ingimundarson, Steinunn Rut Fri{\dh}riksd\'ottir, Bjarki \'Armannsson, Iris Edda Nowenstein, Stein{\th}\'or Steingr\'imsson 3/18/2026

Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic

Study identifying flaws in LLM benchmarks for Icelandic, highlighting issues with synthetic and machine-translated evaluation data.

Ax Abhinav Thorat, Ravi Kolla, Jyotin Goel, Niranjan Pedanekar 3/18/2026

PlotTwist: A Creative Plot Generation Framework with Small Language Models

PlotTwist creative plot generation framework using small language models with specialized training for narrative coherence.

Ax Hong Jeong 3/18/2026

Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods

Method for adding persistent memory to frozen encoder-decoder LLMs via trainable adapters in continuous latent space.

Ax Zhenghua Bao, Yi Shi 3/18/2026

IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time

IndexRAG approach for multi-hop question answering that performs cross-document reasoning at indexing time using bridge entities.

Ax Masakazu Yoshimura, Teruaki Hayashi, Yuki Hoshino, Wei-Yao Wang, Takeshi Ohashi 3/18/2026

SF-Mamba: Rethinking State Space Model for Vision

SF-Mamba state space model for vision addressing non-causal patch interactions with improved computational efficiency.

Ax Ruijia Yang, Zeyi Wen 3/18/2026

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

SlideFormer system for fine-tuning large language models on single GPU via asynchronous engine and sliding window approach.

Ax G. Ciarfaglia, A. Rosanova, S. Cipolla, J. Bartoli, A. Di Domenico, C. Fioroni, A. Fontana, M. R. Scoleri, M. I. Mone, D. Franchi, M. C. Del Gaudio, F. Picariello, M. Gabusi, S. Bonura, V. Morreale, I. Bailo 3/18/2026

EngGPT2: Sovereign, Efficient and Open Intelligence

EngGPT2-16B open Italian LLM trained on 2.5T tokens, efficient inference with performance comparable to larger models.

Ax Marios Aristodemou, Yasaman Omid, Sangarapillai Lambotharan, Mahsa Derakhshan, Lajos Hanzo 3/18/2026

Multi-Agent Reinforcement Learning Counteracts Delayed CSI in Multi-Satellite Systems

Multi-agent reinforcement learning approach for managing delayed channel state information in multi-satellite communication systems.

Ax Hyundo Choi, Junhyeong An, Jinseong Park, Jaewoong Choi 3/18/2026

Unlearning for One-Step Generative Models via Unbalanced Optimal Transport

Unlearning method for one-step generative models using unbalanced optimal transport for safer image generation.

Ax Subina Khanal, Seshu Tirupathi, Merim Dzaferagic, Marco Ruffini, Torben Bach Pedersen 3/18/2026

Bridging the High-Frequency Data Gap: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models

LenghuSky-8 millisecond-resolution network dataset for time series foundation models with high-frequency data.

Ax Zhenghang Song, Tang Qian, Lu Chen, Yushuai Li, Zhengke Hu, Bingbing Fang, Yumeng Song, Junbo Zhao, Sheng Zhang, Tianyi Li 3/18/2026

FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data

FEAT foundation model with linear complexity for structured data in healthcare, finance, and e-commerce with improved scalability.

Ax Lei Wang, Min Huang, Eduard Dragut 3/18/2026

DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis

DanceHA multi-agent framework for document-level aspect-based sentiment analysis, extracting ACOSI tuples from documents.

Ax Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier 3/18/2026

CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

CompDiff uses hierarchical compositional diffusion to generate fair medical images across demographic groups and intersections.

Ax Yifei Zhang, Mingyang Li, Henry Gao, Liang Zhao 3/18/2026

EmoLLM: Appraisal-Grounded Cognitive-Emotional Co-Reasoning in Large Language Models

EmoLLM framework integrates appraisal-grounded cognitive-emotional reasoning into LLMs for contextually appropriate responses.

Ax Jared Moore, Ashish Mehta, William Agnew, Jacy Reese Anthis, Ryan Louie, Yifan Mai, Peggy Yin, Myra Cheng, Samuel J Paech, Kevin Klyman, Stevie Chancellor, Eric Lin, Nick Haber, Desmond C. Ong 3/18/2026

Characterizing Delusional Spirals through Human-LLM Chat Logs

Analysis of human-LLM chat logs characterizing delusional spirals and negative psychological effects from extended chatbot interactions.

Ax Laurent Cheret, Vincent L\'etourneau, Isar Nejadgholi, Chris Drummond, Hussein Al Osman, Maia Fraser 3/18/2026

Manifold-Matching Autoencoders

Manifold-Matching Autoencoders regularize autoencoders by aligning pairwise distances between latent and input spaces.

Ax Florian Holzbauer, David Schmidt, Gabriel Gegenhuber, Sebastian Schrittwieser, Johanna Ullrich 3/18/2026

Malicious Or Not: Adding Repository Context to Agent Skill Classification

Research on classifying malicious AI agent skills using repository context to improve detection in skill marketplaces.

Ax Yong Zou, Haoran Li, Fanxiao Li, Shenyang Wei, Yunyun Dong, Li Tang, Wei Zhou, Renyang Liu 3/18/2026

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models

REFORGE reveals vulnerabilities in image generation model unlearning through multi-modal adversarial attacks in black-box settings.

Ax Ji-Fu Li, Manyi Zhang, Xiaobo Xia, Han Bao, Haoli Bai, Zhenhua Dong, Xianzhi Yu 3/18/2026

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization

BATQuant proposes outlier-resilient MXFP4 quantization via learnable block-wise optimization for deploying MLLMs and LLMs on accelerators.

Ax Redwan Sony, Anil K Jain, Ross Arun 3/18/2026

MLLM-based Textual Explanations for Face Comparison

Analysis of multimodal LLM-generated natural language explanations for face verification on unconstrained face images.

Ax Xiaojie Gu, Sherry T. Tong, Aosong Feng, Sophia Simeng Han, Jinghui Lu, Yingjian Chen, Yusuke Iwasawa, Yutaka Matsuo, Chanjun Park, Rex Ying, Irene Li 3/18/2026

Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models

Omanic, a benchmark for step-wise evaluation of multi-hop reasoning in LLMs with step-level annotations for diagnosing failures.

Ax Aishwarya Ramasethu, Niyathi Allu, Rohin Garg, Harshwardhan Fartale, Dun Li Chan 3/18/2026

Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?

Investigation of linguistically related language guidance for LLM translation in low-resource settings without large parallel data.

Ax Eason Chen, Ce Guan, Ahmed Elshafiey, Zhonghao Zhao, Joshua Zekeri, Afeez Edeifo Shaibu, Emmanuel Osadebe Prince, Cyuan-Jhen Wu 3/18/2026

When Openclaw Agents Learn from Each Other: Insights from Emergent AI Agent Communities for Human-AI Partnership in Education

Study of emergent AI agent communities on platforms, analyzing 167k+ agents learning from each other without researcher intervention.

Ax Jiawei Mao, Hardy Chen, Haoqin Tu, Yuhan Wang, Letian Zhang, Zeyu Zheng, Huaxiu Yao, Zirui Wang, Cihang Xie, Yuyin Zhou 3/18/2026

Kestrel: Grounding Self-Refinement for LVLM Hallucination Mitigation

Kestrel, a training-free method for mitigating hallucinations in large vision-language models using grounding and self-refinement.

Ax Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao 3/18/2026

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

World action models for embodied control that eliminate test-time future imagination while maintaining action performance.

Ax Jun Liu, Pu Zhao, Zhenglun Kong, Xuan Shen, Peiyan Dong, Fan Yang, Lin Cui, Hao Tang, Geng Yuan, Wei Niu, Wenbin Zhang, Xue Lin, Gaowen Liu, Yanzhi Wang, Dong Huang 3/18/2026

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

Resource-aware LLM-based agent reasoning for embodied robots using reinforcement learning to balance computation and action execution.

Ax Guangzhi Xiong, Sanchit Sinha, Zhenghao He, Aidong Zhang 3/18/2026

Retrieving Counterfactuals Improves Visual In-Context Learning

In-context learning improvement for vision-language models using retrieved counterfactuals for better visual reasoning.

Ax D. Darankoum, C. Habermacher, J. Volle, S. Grudinin 3/18/2026

SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding

SpecMoE mixture-of-experts foundation model for cross-species EEG decoding with spectral-temporal fusion.

Ax Jay Chooi, Paul G\"olz, Ariel D. Procaccia, Benjamin Schiffer, Shirley Zhang 3/18/2026

Finding Common Ground in a Sea of Alternatives

Formal model for selecting statements that find common ground across diverse preferences using generative AI.

Ax Victoria Graf, Valentina Pyatkin, Nouha Dziri, Nathan Lambert, Hannaneh Hajishirzi 3/18/2026

TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities

TurnWiseEval benchmark and analysis of multi-turn vs single-turn LLM capabilities with step-level evaluation.

Ax Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, Shawn Guo, Haowen Wang, Weicheng Gu, Yaxin Du, Joseph Li, Fanglin Xu, Yizhi Li, Lin Jing, Yuanbo Wang, Yuhan Gao, Ruihao Gong, Chuan Hao, Ran Tao, Aishan Liu, Tuney Zheng, Ganqu Cui, Zhoujun Li, Mingjie Tang, Chenghua Lin, Wayne Xin Zhao, Xianglong Liu, Ming Zhou, Bryan Dai, Weifeng Lv 3/18/2026