Isolater - Feed

Ax Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Sonia Joseph, Ekdeep S. Lubana, Talia Konkle, Demba Ba, Martin Wattenberg 3/2/2026

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Interpretability study of DINOv2 vision model using sparse autoencoders to analyze task-relevant concept representations.

Ax Zonghuan Xu, Xiang Zheng, Xingjun Ma, Yu-Gang Jiang 3/2/2026

DropVLA: An Action-Level Backdoor Attack on Vision--Language--Action Models

Backdoor attack on vision-language-action models demonstrating vulnerability to behavioral hijacking via hidden training triggers.

Ax Fengzhi Guo, Chih-Chuan Hsu, Sihao Ding, Cheng Zhang 3/2/2026

Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction

Dynamic Gaussian Splatting improvement for monocular 4D scene reconstruction using uncertainty quantification.

Ax Nicolas Menet, Aleksandar Terzi\'c, Michael Hersche, Andreas Krause, Abbas Rahimi 3/2/2026

Thompson Sampling via Fine-Tuning of LLMs

Bayesian optimization method using LLM fine-tuning to perform Thompson sampling in large discrete spaces without gradient computation.

Ax Shingo Ayabe, Hiroshi Kera, Kazuhiko Kawamoto 3/2/2026

Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control

Offline-to-online reinforcement learning framework with adversarial fine-tuning for robust robot control under action perturbations.

Ax Tianwei Wang, Xinhui Ma, Wei Pang 3/2/2026

Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules

Quaternion-valued Hopfield-structured neural network with supervised learning rules for continuous-time dynamical systems.

Ax Yuhan Liu, Lianhui Qin, Shengjie Wang 3/2/2026

Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation

Training-free framework for improving vision-language models on information-dense images with text and graphical elements.

Ax Eeham Khan, Firas Saidani, Owen Van Esbroeck, Richard Khoury, Leila Kosseim 3/2/2026

Low-Resource Dialect Adaptation of Large Language Models: A French Dialect Case-Study

Study of continual pre-training for adapting LLMs to low-resource French dialects under tight compute and data constraints.

Ax Shenran Wang, Timothy Tin-Long Tse, Jian Zhu 3/2/2026

Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures

Investigation of in-context learning across transformer, state-space, and hybrid LLM architectures using behavioral and intervention methods.

Ax Gabrielle O'Brien, Antonio Pedro Santos Alves, Sebastian Baltes, Grischa Liebel, Mircea Lungu, Marcos Kalinowski 3/2/2026

User Misconceptions of LLM-Based Conversational Programming Assistants

Study of misconceptions novice programmers have about LLM-based coding assistants, examining impact of tool capabilities and extensions.

Ax Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei Chen, Wei Wang, Tomas Pfister, Chen-Yu Lee 3/2/2026

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Training method combining supervised learning and reinforcement learning to improve multi-step reasoning in open-source LLMs.

Ax Jack Hong, Chenxiao Zhao, ChengLin Zhu, Weiheng Lu, Guohai Xu, Xing Yu 3/2/2026

DeepEyesV2: Toward Agentic Multimodal Model

Agentic multimodal model framework enabling tool invocation (code execution, web search) and reasoning integration for vision-language tasks.

Ax Davi Bastos Costa, Felippe Alves, Renato Vicente 3/2/2026

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models

Analysis of how LLMs shift moral judgments under persona role-play, introducing benchmark metrics for moral susceptibility and robustness.

Ax Rasmus F. Orsoe, Stephan Meighen-Berger, Jeffrey Lazar, Jorge Prado, Ivan Mozun-Mateo, Aske Rosted, Philip Weigel, Arturo Llorente Anaya 3/2/2026

NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes

Open benchmark for deep learning-based event reconstruction in neutrino telescope data using inverse problem solving.

Ax Vaibhav Singh, Oleksiy Ostapenko, Pierre-Andr\'e No\"el, Eugene Belilovsky, Torsten Scholak 3/2/2026

DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone

Diffusion language model using Mamba backbone for efficient inference, achieving higher throughput than transformer-based alternatives.

Ax Jieru Lin, Zhiwei Yu, B\"orje F. Karlsson 3/2/2026

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios

Benchmark for evaluating embodied AI agents on interaction with physical interfaces (switches, panels, GUIs) in complex environments.

Ax Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen 3/2/2026

Score-Regularized Joint Sampling with Importance Weights for Flow Matching

Novel sampling framework for flow matching models using importance weighting to improve variance reduction in expectation estimation.

Ax Juvenal Bassa, Arghya Chattopadhyay, Sudhir Malik, Mario Escabi Rivera 3/2/2026

MEDIC: a network for monitoring data quality in collider experiments

Machine learning system for automating data quality monitoring and anomaly detection in particle physics collider experiments.

Ax Helia Abedini, Saba Rahimi, Reza Vaziri 3/2/2026

General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification

Study comparing CNN pretraining strategies (general vs domain-specific) for brain tumor classification in MRI images with limited data.

Ax Ziyi Chen, Yingnan Guo, Zedong Chu, Minghua Luo, Yanfen Shen, Mingchao Sun, Junjun Hu, Shichao Xie, Kuan Yang, Pei Shi, Zhining Gu, Lu Liu, Honglin Han, Xiaolong Wu, Mu Xu, Yu Zhang, Ning Guo 3/2/2026

SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation

SocialNav foundation model for socially-aware embodied navigation with hierarchical architecture trained on 7M samples for human-compliant trajectory generation.

Ax Tao Zhe, Huazhen Fang, Kunpeng Liu, Qian Lou, Tamzidul Hoque, Dongjie Wang 3/2/2026

Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation

Heterogeneous multi-agent reinforcement learning with attention mechanism for automated feature transformation on structured data.

Ax Zhijian Wei, Runze Ma, Zichen Wang, Zhongmin Li, Shuotong Song, Shuangjia Zheng 3/2/2026

VCWorld: A Biological World Model for Virtual Cell Simulation

VCWorld biological world model for virtual cell simulation predicting cellular responses to perturbations using multi-source biological information.

Ax Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Kuo-Chung Peng, Nan-Yow Chen, Samuel Yen-Chi Chen, En-Jui Kuo, Hsi-Sheng Goan 3/2/2026

QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory

QKAN-LSTM combining quantum-inspired Kolmogorov-Arnold networks with LSTM for improved sequential modeling with reduced parameter redundancy.

Ax Li Ju, Jun Zhao, Mingxu Chai, Ziyu Shen, Xiangyang Wang, Yage Geng, Chunchun Ma, Hao Peng, Guangbin Li, Tao Li, Chengyong Liao, Fu Wang, Xiaolong Wang, Junshen Chen, Rui Gong, Shijia Liang, Feiyan Li, Ming Zhang, Kexin Tan, Junjie Ye, Zhiheng Xi, Shihan Dou, Tao Gui, Yuankai Ying, Yang Shi, Yue Zhang, Qi Zhang 3/2/2026

WisPaper: Your AI Scholar Search Engine

WisPaper end-to-end agent system for academic literature discovery and organization combining semantic search verification with workflow integration.

Ax Jiyoon Pyo, Yuankun Jiao, Dongwon Jung, Zekun Li, Leeje Jang, Sofia Kirsanova, Jina Kim, Yijun Lin, Qin Liu, Junyi Xie, Hadi Askari, Nan Xu, Muhao Chen, Yao-Yi Chiang 3/2/2026

FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models

FRIEDA benchmark evaluating vision-language models on multi-step cartographic reasoning with map interpretation for disaster response and urban planning.

Ax Bart{\l}omiej Starosta, S{\l}awomir T. Wierzcho\'n, Piotr Borkowski, Dariusz Czerski, Marcin Sydow, Eryk Laskowski, Mieczys{\l}aw A. K{\l}opotek 3/2/2026

Rough Sets for Explainability of Spectral Graph Clustering

Rough sets methodology for explaining spectral graph clustering results on text documents with handling of documents without clear content meaning.

Ax Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi, Lin Xiao 3/2/2026

Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs

Generalized Primal Averaging optimizer extending Nesterov's method for faster LLM training, unifying DiLoCo and schedule-free approaches with reduced memory requirements.

Ax Yingru Li, Jiacai Liu, Jiawei Xu, Yuxuan Tong, Ziniu Li, Qian Liu, Baoxiang Wang 3/2/2026

Trust Region Masking for Long-Horizon LLM Reinforcement Learning

Trust region masking technique for LLM reinforcement learning addressing off-policy mismatch and approximation errors from implementation divergences in policy gradient optimization.

Ax Arsham Khosravani, Alireza Hoseinpour, Arshia Akhavan, Mehdi Keshani, Abbas Heydarnoori 3/2/2026

LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment

LIA supervised fine-tuning approach using LLMs for automatic software issue assignment in large open-source projects without heavy project-specific training data.

Ax Hengyu Liu, Tianyi Li, Haoyu Wang, Kristian Torp, Tiancheng Zhang, Yushuai Li, Christian S. Jensen 3/2/2026

VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenance

VISTA method for repairing incomplete maritime vessel trajectory data with repair provenance documentation for safety-critical applications.

Ax Boyang Wang, Yash Vishe, Xin Xu, Zachary Novack, Xunyi Jiang, Julian McAuley, Junda Wu 3/2/2026

CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning

CSyMR benchmark for compositional music information retrieval testing LLMs on multi-step reasoning over symbolic music scores and natural language queries.

Ax Maurice Filo, Nicol\`o Rossi, Zhou Fang, Mustafa Khammash 3/2/2026

GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Design

GenAI-Net generative framework for automated design of chemical reaction networks implementing desired dynamical functions in synthetic biology applications.

Ax Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu 3/2/2026

DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher

DUET method for LLM unlearning via distillation from a contextualized teacher, removing undesirable knowledge without retraining while avoiding catastrophic forgetting.

Ax Yikai Zeng, Yingchao Piao, Changhua Pei, Jianhui Li 3/2/2026

LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs

LEC-KG framework combining LLM semantic understanding with knowledge graph embeddings for automated domain-specific knowledge graph construction from unstructured text.

Ax Quanquan Peng, Yunfeng Lin, Yufei Xue, Jiangmiao Pang, Weinan Zhang 3/2/2026

Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

Reinforcement learning approach for training humanoid whole-body controllers that generalize across diverse robot embodiments with varied dynamics and degrees of freedom.

Ax Farnoosh Hashemi, Michael W. Macy 3/2/2026

An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents

Empirical study of 32K LLM agents on Chirper.ai social media platform analyzing collective behaviors, biases, and exclusionary dynamics across 7M posts.

Ax Xukun Li, Yu Sun, Lei Zhang, Bosheng Huang, Yibo Peng, Yuan Meng, Haojun Jiang, Shaoxuan Xie, Guocai Yao, Alois Knoll, Zhenshan Bing, Xinlong Wang, Zhenguo Sun 3/2/2026

DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter

Multimodal diffusion transformer for robotic bimanual dexterous manipulation integrating vision, proprioception, and tactile signals.

Ax Dominik P. Hofer, David Haag, Rania Islambouli, Jan D. Smeddinck 3/2/2026

Personality as Relational Infrastructure: User Perceptions of Personality-Trait-Infused LLM Messaging

Study on how LLM-generated personalized messages in behavior-change systems affect user perceptions through exposure patterns rather than individual message quality.

Ax Savan Doshi 3/2/2026

Beyond Accuracy: Risk-Sensitive Evaluation of Hallucinated Medical Advice

Risk-sensitive evaluation framework for LLM hallucinations in medical advice, assessing clinical harm severity beyond factual correctness.

Ax Iv\'an Arcuschin, David Chanin, Adri\`a Garriga-Alonso, Oana-Maria Camburu 3/2/2026

Biases in the Blind Spot: Detecting What LLMs Fail to Mention

Automated black-box pipeline detecting unverbalized biases in LLM chain-of-thought reasoning without predefined categories using task-specific evaluation.

Ax Zhen Bi, Xueshu Chen, Luoyang Sun, Yuhang Yao, Qing Shen, Jungang Lou, Cheng Deng 3/2/2026

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis

RooflineBench: Roofline model-based benchmarking framework for characterizing performance of Small Language Models on edge hardware.

Ax Pengfei Zhang, Tianxin Xie, Minghao Yang, Li Liu 3/2/2026

Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis

Agentic system for respiratory disease diagnosis using multimodal sound generation and active adversarial curriculum learning.

Ax Daniel Romero-Alvarado, Fernando Mart\'inez-Plumed, Lorenzo Pacchiardi, Hugo Save, Siddhesh Milind Pawar, Behzad Mehrbakhsh, Pablo Antonio Moreno Casares, Ben Slater, Paolo Bova, Peter Romero, Zachary R. Tyler, Jonathan Prunty, Luning Sun, Jose Hernandez-Orallo 3/2/2026