Isolater - Feed

Ax KC Santosh, Srikanth Baride, Rodrigue Rizk 2/25/2026

AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models

AI-CARE metric for evaluating ML models on carbon emissions and energy consumption alongside standard performance metrics.

Ax Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si 2/25/2026

Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

Research on interpretable Graph Neural Networks using symbolic methods to overcome message-passing limitations and Weisfeiler-Lehman expressivity barriers.

Ax Chuqin Geng, Li Zhang, Mark Zhang, Haolin Ye, Ziyu Zhao, Xujie Si 2/25/2026

Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints

Neuro-symbolic framework (NSGGM) for molecule and graph generation combining neural proposals with symbolic guarantees for controllable generation.

Ax Ziliang Zhao, Bi Xue, Emma Lin, Mengjiao Zhou, Kaustubh Vartak, Shakhzod Ali-Zade, Tianqi Lu, Tao Li, Bin Kuang, Rui Jian, Bin Wen, Dennis van der Staay, Yixin Bao, Eddy Li, Chao Deng, Songbin Liu, Qifan Wang, Kai Ren 2/25/2026

Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders

MPZCH indexing mechanism for large-scale recommendation systems to mitigate embedding collisions and improve model freshness in embedding tables.

Ax Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai 2/25/2026

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning

MASPO algorithm for LLM reasoning via reinforcement learning, addressing gradient utilization, probability mass, and signal reliability in trust region mechanisms.

Ax Corinna Cortes, Mehryar Mohri, Yutao Zhong 2/25/2026

A Theoretical Framework for Modular Learning of Robust Generative Models

Theoretical framework for training modular LLMs by combining domain-specific experts without heuristic dataset weighting, matching monolithic model performance.

Ax Sima Noorani, Shayan Kiyani, Hamed Hassani, George Pappas 2/25/2026

Multi-Round Human-AI Collaboration with User-Specified Requirements

Framework for multi-round human-AI collaboration ensuring AI complements rather than undermines human decision-making via counterfactual harm and complementarity principles.

Ax Rampunit Kumar, Aditya Maheshwari 2/25/2026

NEXUS: A compact neural architecture for high-resolution spatiotemporal air quality forecasting in Delhi National Capital Region

NEXUS neural architecture for air quality forecasting in Delhi using spatiotemporal data. Achieves R² > 0.94 for CO prediction.

Ax Mina Ghashami, Soumya Smruti Mishra 2/25/2026

Augmenting Lateral Thinking in Language Models with Humor and Riddle Data for the BRAINTEASER Task

Fine-tuned DeBERTaV3 system for lateral thinking in language models using humor/riddle data on BRAINTEASER task. LLM reasoning research.

Ax Patrick Chao, Yan Sun, Edgar Dobriban, Hamed Hassani 2/25/2026

Watermarking Language Models with Error Correcting Codes

Error correcting code based watermarking framework for detecting machine-generated text in language models. LLM safety research.

Ax Siddharth Chandak, Ilai Bistritz, Nicholas Bambos 2/25/2026

Learning to Control Unknown Strongly Monotone Games

Game theory research on controlling strongly monotone games via gradient play and generalized Nash equilibrium constraints.

Ax Sofya Manko, Dmitry Frolovtsev 2/25/2026

Classification and reconstruction for single-pixel imaging with classical and quantum neural networks

Quantum and classical neural networks for single-pixel imaging classification. Quantum ML research with imaging application.

Ax Weichen Wu, Gen Li, Yuting Wei, Alessandro Rinaldo 2/25/2026

Statistical Inference for Temporal Difference Learning with Linear Function Approximation

Theoretical analysis of Temporal Difference learning convergence with linear function approximation. Foundational RL research.

Ax Mehran Shabanpour, Kasra Rad, Sadaf Khademi, Arash Mohammadi 2/25/2026

MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition

Mamba-based Mixture of Experts architecture for EMG gesture recognition. Machine learning research with practical HCI application.

Ax Miao Li, Michael Klamkin, Russell Bent, Pascal Van Hentenryck 2/25/2026

Tightening Optimality gap with confidence through conformal prediction

Conformal prediction method for assessing optimality gaps in constrained optimization for decision-making in complex systems like supply chains.

Ax Juhyeon Park, Peter Yongho Kim, Jiook Cha, Shinjae Yoo, Taesup Moon 2/25/2026

SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding

SEED metric for semantic evaluation of visual brain decoding models, integrating three complementary metrics aligned with human evaluation data.

Ax Prashant Garg, Thiemo Fetzer 2/25/2026

How much does context affect the accuracy of AI health advice?

Evaluation of seven LLMs on health-claim verification across languages and contexts, assessing how linguistic and contextual factors affect accuracy of AI-generated health advice.

Ax Daniel J. Strick, Carlos Garcia, Anthony Huang, Thomas Gardos 2/25/2026

Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification

Reproduction and improvement of CheXNet for chest X-ray disease classification on NIH ChestX-ray14 dataset with deep learning models.

Ax Soham Bonnerjee, Sayar Karmakar, Wei Biao Wu 2/25/2026

Sharp Gaussian approximations for Decentralized Federated Learning

Research on Gaussian approximations for decentralized federated learning with local SGD, providing asymptotic statistical guarantees for privacy-sensitive distributed optimization.

Ax Chuhao Zhou, Jianfei Yang 2/25/2026

HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning

HoloLLM is a multimodal LLM for embodied agents in smart homes that processes diverse sensory inputs beyond vision for language-grounded perception and human behavior understanding.

Ax Agnideep Aich, Md Monzur Murshed, Sameera Hewage, Amanda Mayeaux 2/25/2026

A Copula Based Supervised Filter for Feature Selection in Diabetes Risk Prediction Using Machine Learning

Feature selection filter using copula-based tail concordance scoring for diabetes risk prediction model interpretability.

Ax Florian F\"urrutter, Zohim Chandani, Ikko Hamamura, Hans J. Briegel, Gorka Mu\~noz-Gil 2/25/2026

Synthesis of discrete-continuous quantum circuits with multimodal diffusion models

Diffusion model approach for synthesizing discrete-continuous quantum circuits to reduce compilation overhead in quantum computing.

Ax Apurv Verma, NhatHai Phan, Shubhendu Trivedi 2/25/2026

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation

Analysis showing watermarking degrades LLM alignment safety properties and proposes mitigation strategies for deployment compatibility.

Ax J\^onata Tyska Carvalho, Stefano Nolfi 2/25/2026

Sensory-Motor Control with Large Language Models via Iterative Policy Refinement

Method enabling LLMs to generate and iteratively refine continuous control policies for embodied agent sensory-motor control.

Ax Gon\c{c}alo Hora de Carvalho, Lazar S. Popov, Sander Kaatee, M\'ario S. Correia, Kristinn R. Th\'orisson, Tangrui Li, P\'etur H\'uni Bj\"ornsson, Eir\'ikur Sm\'ari Sigur{\dh}arson, Jilles S. Dibangoye 2/25/2026

ICE-ID: A Novel Historical Census Dataset for Longitudinal Identity Resolution

Benchmark dataset of 984K historical Icelandic census records for evaluating identity resolution algorithms across 220 years.

Ax Lukas Gonon, Rodrigo Mart\'inez-Pe\~na, Juan-Pablo Ortega 2/25/2026

Feedback-driven recurrent quantum neural network universality

Theoretical analysis of feedback-driven quantum reservoir computing for temporal machine learning on intermediate-scale quantum devices.

Ax Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktaschel, Jakob Foerster, Laura Ruis 2/25/2026

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs

Training method enabling LLMs to learn procedural knowledge from declarative instructions, demonstrating instruction efficiency in fine-tuning.

Ax Jiechen Chen, Bipin Rajendran, Osvaldo Simeone 2/25/2026

Stochastic Quantum Spiking Neural Networks with Quantum Memory and Local Learning

Hybrid approach combining spiking neural networks with quantum computing for neuromorphic AI with temporal data processing.

Ax Pierre Boudart (SIERRA), Pierre Gaillard (Thoth), Alessandro Rudi (PSL, DI-ENS, Inria) 2/25/2026

Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm

Theoretical analysis of multinomial logistic bandits with minimax-optimal algorithm addressing non-linearity in feedback mechanisms.

Ax Saptarshi Mitra, Rachid Karami, Haocheng Xu, Sitao Huang, Hyoukjun Kwon 2/25/2026

Characterizing State Space Model and Hybrid Language Model Performance with Long Context

Comparative analysis of State Space Model and hybrid architectures versus Transformers for long-context processing on edge devices.

Ax Ayush Roy, Samin Enam, Jun Xia, Won Hwa Kim, Vishnu Suresh Lokhande 2/25/2026

Is Exchangeability better than I.I.D to handle Data Distribution Shifts while Pooling Data for Data-scarce Medical image segmentation?

Study comparing exchangeability assumptions versus i.i.d. assumptions for handling distribution shifts in pooled medical imaging datasets.

Ax Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso 2/25/2026

TASER: Table Agents for Schema-guided Extraction and Recommendation

LLM-based agent system for schema-guided extraction and recommendation from financial tables with missing structural metadata.

Ax Nuno Costa, Julija Zavadlav 2/25/2026

Morphology-Aware Peptide Discovery via Masked Conditional Generative Modeling

Generative modeling pipeline for peptide discovery that predicts aggregate morphology and generates novel biocompatible sequences.

Ax Jeongjae Lee, Jong Chul Ye 2/25/2026

PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models

Policy optimization method addressing credit assignment problems in reinforcement learning for aligning text-to-image generation models.

Ax Didrik Bergstr\"om, Deniz G\"und\"uz, Onur G\"unl\"u 2/25/2026

Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Recovery

Deep joint source-channel coding method with hash distillation for semantic image transmission over multi-hop channels.

Ax Chengshu Li, Mengdi Xu, Arpit Bahety, Hang Yin, Yunfan Jiang, Huang Huang, Josiah Wong, Sujay Garlanka, Cem Gokmen, Ruohan Zhang, Weiyu Liu, Jiajun Wu, Roberto Mart\'in-Mart\'in, Li Fei-Fei 2/25/2026

MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Framework for automatically generating demonstrations for training multi-step bimanual mobile manipulation robots under soft and hard constraints.

Ax Roxanne Holden, Luana Ruiz 2/25/2026

A Spectral Framework for Graph Neural Operators: Convergence Guarantees and Tradeoffs

Theoretical framework analyzing convergence properties of graph neural operators using spectral analysis and graphon theory.

Ax Julia Bazinska, Max Mathys, Francesco Casucci, Mateo Rojas-Carulla, Xander Davies, Alexandra Souly, Niklas Pfister 2/25/2026

Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents

Research evaluating security vulnerabilities of backbone LLMs used in AI agents, addressing systematic security modeling for deployed agent systems.

Ax Raphael Schwinger, Ben McEwen, Vincent S. Kather, Ren\'e Heinrich, Lukas Rauch, Sven Tomforde 2/25/2026

Uncertainty Calibration of Multi-Label Bird Sound Classifiers

Deep learning approach for calibrating uncertainty estimates in multi-label bird sound classifiers for bioacoustic monitoring.

Ax Ang Lv, Jin Ma, Yiyuan Ma, Siyuan Qiao 2/25/2026

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

Research on expert-router coupling loss for mixture-of-experts models to align router decisions with expert capabilities.

Ax Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz, Yu-Chiang Frank Wang, Fu-En Yang 2/25/2026

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

Fast-ThinkAct framework for efficient vision-language-action reasoning using compact latent planning to reduce inference latency.

Ax Quoc Hoan Tran, Koki Chinzei, Yasuhiro Endo, Hirotaka Oshima 2/25/2026

Universality of Many-body Projected Ensemble for Learning Quantum Data Distribution

Theoretical proof of universality for many-body quantum machine learning models in approximating quantum distributions.

Ax Haozheng Luo, Zhuolin Jiang, Md Zahid Hasan, Yan Chen, Soumalya Sarkar 2/25/2026

FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning

FROST method for efficient LLM reasoning by pruning uncritical paths using attention weights to reduce inference latency.

Ax Shun Takagi, Seng Pei Liew 2/25/2026

Analysis of Shuffling Beyond Pure Local Differential Privacy

Theoretical analysis of privacy amplification in shuffled data analysis beyond local differential privacy bounds.

Ax Weining Fu, Kai Shu, Kui Xu, Qiangfeng Cliff Zhang 2/25/2026

CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models

Self-supervised learning framework applying vision models to cryo-EM density maps for structural biology analysis.

Ax Aqsa Sultana, Rayan Afsar, Ahmed Rahu, Surendra P. Singh, Brian Shula, Brandon Combs, Derrick Forchetti, Vijayan K. Asari 2/25/2026

XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas

Deep learning model for classifying neoplastic tubular adenomas in colonoscopy screenings using medical image analysis.

Ax Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin 2/25/2026

GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing

Research on object tracking using 3D geometric reasoning and online model editing to handle occlusion and appearance variations.

Ax Venus Team, Changlong Gao, Zhangxuan Gu, Yulin Liu, Xinyu Qiu, Shuheng Shen, Yue Wen, Tianyu Xia, Zhenyu Xu, Zhengwen Zeng, Beitong Zhou, Xingran Zhou, Weizhi Chen, Sunhao Dai, Jingya Dou, Yichen Gong, Yuan Guo, Zhenlin Guo, Feng Li, Qian Li, Jinzhen Lin, Yuqi Zhou, Linchao Zhu, Liang Chen, Zhenyu Guo, Changhua Meng, Weiqiang Wang 2/25/2026