Isolater - Feed

Ax Sushant Mehta, Logan Ritchie, Suhaas Garre, Nick Heiner, Edwin Chen 2/20/2026

EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments

CoreCraft: enterprise RL environment for training generalizable AI agents in customer support simulation with 2,500+ entities and 23 tools.

Ax Yung-Chen Tang, Pin-Yu Chen, Tsung-Yi Ho 2/20/2026

Defining and Evaluating Physical Safety for Large Language Models

Benchmark evaluating physical safety risks of LLMs controlling robotic systems, categorizing drone-related threats and harms.

Ax Aditya Dutt, Ishikaa Lunawat, Manpreet Kaur 2/20/2026

Multi-View 3D Reconstruction using Knowledge Distillation

Knowledge distillation pipeline to compress Dust3r foundation model for faster 3D reconstruction and visual localization.

Ax Jangseop Park, Namwoo Kang 2/20/2026

Point-DeepONet: Predicting Nonlinear Fields on Non-Parametric Geometries under Variable Load Conditions

Operator-learning surrogate model combining PointNet and DeepONet for nonlinear field prediction on complex geometries.

Ax Sanghyeon Lee, Sangjun Bae, Yisak Park, Seungyul Han 2/20/2026

Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning

Meta-RL approach using skill decomposition with improved robustness to noisy offline demonstrations for long-horizon tasks.

Ax Zander W. Blasingame, Chen Liu 2/20/2026

Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers

Rex reversible exponential Runge-Kutta solvers for neural differential equations in generative models.

Ax Alan Luo, Kaiwen Yuan 2/20/2026

Simple Self Organizing Map with Vision Transformers

Self-organizing maps combined with vision transformers to improve ViT performance on small datasets.

Ax Ting Qiao, Yingjia Wang, Xing Liu, Sixing Wu, Jianbin Li, Yiming Li 2/20/2026

Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises

Certified backdoor defense for DNNs using sample-specific smoothing noise against training data poisoning attacks.

Ax Dmitriy Shopkhoev, Ammar Ali, Magauiya Zhussip, Valentin Malykh, Stamatios Lefkimmiatis, Nikos Komodakis, Sergey Zagoruyko 2/20/2026

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

ReplaceMe training-free depth pruning method replacing transformer blocks with linear operations for model compression.

Ax Amal Lahchim (University of Kragujevac), Lazar Davic (University of Kragujevac) 2/20/2026

Attention-Enhanced U-Net for Accurate Segmentation of COVID-19 Infected Lung Regions in CT Scans

U-Net CNN with attention mechanisms for COVID-19 lung segmentation in CT scans. Medical imaging, not core AI interests.

Ax Adrian Arnaiz-Rodriguez, Federico Errica 2/20/2026

Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

Survey demystifying graph neural network concepts: oversmoothing, oversquashing, heterophily, and long-range dependencies.

Ax Yifan Zhang, Yifeng Liu, Huizhuo Yuan, Yang Yuan, Quanquan Gu, Andrew Chi-Chih Yao 2/20/2026

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning

Research on KL-regularized policy gradient algorithms for LLM reasoning, comparing forward/reverse KL regularization designs.

Ax Eleonora Cappuccio (Department of Computer Science, University of Pisa), Andrea Esposito (Department of Computer Science, University of Bari Aldo Moro), Francesco Greco (Department of Computer Science, University of Bari Aldo Moro), Giuseppe Desolda (Department of Computer Science, University of Bari Aldo Moro), Rosa Lanzilotti (Department of Computer Science, University of Bari Aldo Moro), Salvatore Rinzivillo (ISTI CNR) 2/20/2026

Explanation User Interfaces: A Systematic Literature Review

Systematic literature review of explanation user interfaces for black-box AI systems and XAI techniques.

Ax Yan Wang, Lingfei Qian, Xueqing Peng, Yang Ren, Keyi Wang, Yi Han, Dongji Feng, Fengran Mo, Shengyuan Lin, Qinchuan Zhang, Kaiwen He, Chenri Luo, Jianxing Chen, Junwei Wu, Chen Xu, Ziyang Xu, Jimin Huang, Guojun Xiong, Xiao-Yang Liu, Qianqian Xie, Jian-Yun Nie 2/20/2026

FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information

FinTagging benchmark for evaluating LLMs on financial information extraction and hierarchical GAAP concept classification.

Ax Nguyen-Khang Le, Quan Minh Bui, Minh Ngoc Nguyen, Hiep Nguyen, Trung Vo, Son T. Luu, Shoshin Nomura, Minh Le Nguyen 2/20/2026

Automated Web Application Testing: End-to-End Test Case Generation with Large Language Models and Screen Transition Graphs

Automated web app testing system using LLMs and screen transition graphs for test case generation.

Ax Maximilian Kreutner, Marlene Lutz, Markus Strohmaier 2/20/2026

Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models

Study on persona-driven prompting of LLMs to simulate voting behavior in European Parliament, analyzing progressive bias mitigation.

Ax Jaebak Hwang, Sanghyeon Lee, Jeongmo Kim, Seungyul Han 2/20/2026

Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning

Strict Subgoal Execution method improves long-horizon planning in hierarchical reinforcement learning through reliable subgoal feasibility.

Ax Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues 2/20/2026

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks

MCIF benchmark for evaluating multimodal LLMs on crosslingual instruction-following with long-form inputs from scientific talks.

Ax Ziyi Wang, Ziwen Zeng, Yuan Li, Zijian Ding 2/20/2026

CareerPooler: AI-Powered Metaphorical Pool Simulation Improves Experience and Outcomes in Career Exploration

CareerPooler generative AI system for career exploration using pool-table metaphor simulation instead of linear chat interface.

Ax Anton Selitskiy, Akib Shahriyar, Jishnuraj Prakasan 2/20/2026

Discrete optimal transport is a strong audio adversarial attack

Discrete optimal transport voice conversion method shown as effective black-box adversarial attack on audio anti-spoofing systems.

Ax Shi Yin, Zujian Dai, Xinyang Pan, Lixin He 2/20/2026

Advancing Universal Deep Learning for Electronic-Structure Hamiltonian Prediction of Materials

Deep learning approach for predicting electronic-structure Hamiltonians of materials with improved generalization.

Ax Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Ammar Ali, Stamatios Lefkimmiatis 2/20/2026

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning

CoSpaDi training-free compression method for LLMs using sparse dictionary learning instead of rigid low-rank approximations.

Ax Thibaud Gloaguen, Robin Staab, Nikola Jovanovi\'c, Martin Vechev 2/20/2026

Watermarking Diffusion Language Models

First watermarking scheme designed for diffusion language models that generate tokens in arbitrary order rather than sequentially.

Ax Mahdi Farahbakhsh, Vishnu Teja Kunde, Dileep Kalathil, Krishna Narayanan, Jean-Francois Chamberland 2/20/2026

Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction

Inference-time search algorithm guides diffusion model sampling using side information for improved image reconstruction.

Ax Yumin Choi, Dongki Kim, Jinheon Baek, Sung Ju Hwang 2/20/2026

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs

Prompt optimization framework extended to multimodal LLMs, optimizing visual and textual prompts jointly for improved performance.

Ax Hansheng Chen, Kai Zhang, Hao Tan, Leonidas Guibas, Gordon Wetzstein, Sai Bi 2/20/2026

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

pi-Flow modifies flow-based generative models to predict network-free policies for efficient few-step image generation.

Ax Luca Belli, Kate Bentley, Will Alexander, Emily Ward, Matt Hawrilenko, Kelly Johnston, Mill Brown, Adam Chekroud 2/20/2026

VERA-MH Concept Paper

VERA-MH automated evaluation framework for assessing safety of AI chatbots in mental health contexts using LLM-based agents.

Ax Ximan Sun, Xiang Cheng 2/20/2026

LRT-Diffusion: Calibrated Risk-Aware Guidance for Diffusion Policies

LRT-Diffusion applies risk-aware sampling to diffusion policies for offline reinforcement learning with statistical hypothesis testing.

Ax Chuyue Sun, Yican Sun, Daneshvar Amrollahi, Ethan Zhang, Shuvendu Lahiri, Shan Lu, David Dill, Clark Barrett 2/20/2026

VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus

VeriStruct framework uses LLMs to automate verification of data structure modules in the Verus verification language.

Ax Seonggyun Lee, Sungjun Lim, Seojin Park, Soeun Cheon, Kyungwoo Song 2/20/2026

Semi-Supervised Preference Optimization with Limited Feedback

Semi-Supervised Preference Optimization reduces labeled feedback requirements for aligning language models with human preferences.

Ax Yan Sun, Jia Guo, Stanley Kok, Zihao Wang, Zujie Wen, Zhiqiang Zhang 2/20/2026

Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration

PREPO framework improves data efficiency of reinforcement learning for LLMs by leveraging intrinsic data properties during training.

Ax Taja Kuzman Punger\v{s}ek, Peter Rupnik, Ivan Porupski, Vuk Dini\'c, Nikola Ljube\v{s}i\'c 2/20/2026

State of the Art in Text Classification for South Slavic Languages: Fine-Tuning or Prompting?

Evaluation of fine-tuned BERT vs LLM prompting for text classification on South Slavic languages, a less-resourced language group.

Ax Marius Dubosc, Yann Fischer, Zacharie Auray, Nicolas Boutry, Edwin Carlinet, Michael Atlan, Thierry Geraud 2/20/2026

Improving segmentation of retinal arteries and veins using cardiac signal in doppler holograms

Deep learning method for segmenting retinal blood vessels using temporal information from Doppler holography imaging.

Ax Ahmed Aboulfotouh, Hatem Abou-Zeid 2/20/2026

Multimodal Wireless Foundation Models

Wireless foundation models extended to process multiple modalities for improved task performance across varying operating conditions.

Ax Wangjiaxuan Xin 2/20/2026

Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models

Empathetic Cascading Networks multi-stage prompting framework reduces social biases in LLMs through perspective adoption and emotional resonance stages.

Ax Akash Doshi, Pinar Sen, Kirill Ivanov, Wei Yang, June Namgoong, Runxin Wang, Rachel Wang, Taesang Yoo, Jing Jiang, Tingfang Ji 2/20/2026

AI/ML based Joint Source and Channel Coding for HARQ-ACK Payload

Transformer-based joint source-channel coding for non-uniformly distributed HARQ-ACK bits in wireless communications using deep learning.

Ax Sanjeev Shrestha, Rahul Dubey, Hui Liu 2/20/2026

Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models

Local explanation method using MARS and N-ball sampling for generating high-fidelity explanations of black-box model predictions.

Ax Ryan Banks, Camila Lindoni Azevedo, Hongying Tang, Yunpeng Li 2/20/2026

Restrictive Hierarchical Semantic Segmentation for Stratified Tooth Layer Detection

Framework for semantic segmentation using hierarchy-aware methods to detect stratified tooth layers in dental imaging.

Ax Jonathan Kamp, Roos Bakker, Dominique Blok 2/20/2026

Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution

Reveals lexical and positional biases in post-hoc feature attribution methods like Integrated Gradients, affecting explanation quality for language models.

Ax Mozes Jacobs, Thomas Fel, Richard Hakim, Alessandra Brondetta, Demba Ba, T. Andy Keller 2/20/2026

Block-Recurrent Dynamics in Vision Transformers

Block-Recurrent Hypothesis characterizes Vision Transformer depth as block-recurrent structure, providing mechanistic understanding of ViT computations.

Ax Marie S. Bauer, Julia Gachot, Matthias Kerzel, Cornelius Weber, Stefan Wermter 2/20/2026

Theory of Mind for Explainable Human-Robot Interaction

Framework integrating Theory of Mind into robots for inferring human mental states to enhance explainability and predictability in human-robot interaction.

Ax Bac Nguyen, Yuhta Takida, Naoki Murata, Chieh-Hsin Lai, Toshimitsu Uesaka, Stefano Ermon, Yuki Mitsufuji 2/20/2026

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

CODA extends slot attention with register tokens and contrastive alignment to improve object-centric learning using pretrained diffusion models.

Ax Stephen Gadd 2/20/2026

Symphonym: Universal Phonetic Embeddings for Cross-Script Name Matching

Symphonym neural embedding system maps names across scripts into unified phonetic space for cross-script and cross-language name matching.

Ax Nifu Dan 2/20/2026

Auditing Student-AI Collaboration: A Case Study of Online Graduate CS Students

Mixed-methods audit examining alignment between student preferences and AI system capabilities for collaborative academic tasks in CS education.

Ax Yijun Ma, Zehong Wang, Weixiang Sun, Yanfang Ye 2/20/2026

Temporal Graph Pattern Machine

Temporal graph pattern machine for learning transferable representations from dynamic networks by modeling evolving patterns without restrictive assumptions.

Ax Kapilan Balagopalan, Yinan Li, Yao Zhao, Tuan Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun 2/20/2026

Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

Theoretical analysis proving fixed-budget and fixed-confidence best-arm identification settings have equivalent sample complexity up to logarithmic factors.

Ax Sanjana Reddy (Google), Ishaan Malhi (Google DeepMind), Sally Ma (Google DeepMind), Praneet Dutta (Google DeepMind) 2/20/2026

Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image Generation

Di3PO improves preference tuning of text-to-image diffusion models using diptych diffusion and DPO for efficient training pair generation.

Ax Cen Zhang, Younggi Park, Fabian Fleischer, Yu-Fu Fu, Jiho Kim, Dongkwan Kim, Youngjoon Kim, Qingxiao Xu, Andrew Chin, Ze Sheng, Hanqing Zhao, Brian J. Lee, Joshua Wang, Michael Pelican, David J. Musliner, Jeff Huang, Jon Silliman, Mikel Mcdaniel, Jefferson Casavant, Isaac Goldthwaite, Nicholas Vidovich, Matthew Lehman, Taesoo Kim 2/20/2026