Isolater - Feed

Ax Zhaobo Hu, Vincent Gauthier, Mehdi Naima 4/17/2026

Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks

Research on Doubly Stochastic Matrices for Graph Neural Networks, improving structural message passing with multi-hop proximity encoding.

Ax He Yang, Dongyi Lv, Wei Xi, Song Ma, Hanlin Gu, Jizhong Zhao 4/17/2026

FedIDM: Achieving Fast and Stable Convergence in Byzantine Federated Learning through Iterative Distribution Matching

FedIDM: Byzantine-robust federated learning using distribution matching for fast stable convergence with malicious clients.

Ax Lukas Helff, Quentin Delfosse, David Steinmann, Ruben H\"arle, Hikaru Shindo, Patrick Schramowski, Wolfgang Stammer, Kristian Kersting, Felix Friedrich 4/17/2026

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

RLVR paradigm exhibits reward hacking where LLMs game verifiers instead of learning generalizable rules in reasoning tasks.

Ax Marcus Armstrong 4/17/2026

When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence

INT4 quantization fails after FP32 convergence showing three-phase divergence structure unrelated to loss landscape flatness.

Ax Aleksander Berezowski, Hassan Hassanzadeh, Gouri Ginde 4/17/2026

Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data

Systematic mapping study assessing masked autoencoder foundation models for predicting downhole drilling metrics.

Ax Yoo-Min Jung, Leekyung Kim 4/17/2026

MambaSL: Exploring Single-Layer Mamba for Time Series Classification

MambaSL: single-layer Mamba framework optimized for time series classification with minimal architectural modifications.

Ax Nuno Gon\c{c}alves, Hugo Pitorro, Vlad Niculae, Edoardo Ponti, Lei Li, Andre Martins, Marcos Treviso 4/17/2026

AdaSplash-2: Faster Differentiable Sparse Attention

AdaSplash-2: faster differentiable sparse attention mechanism addressing computational overhead of α-entmax attention.

Ax Teng Ma, Luca Rosafalco, Wei Cui, Lin Zhao, Attilio Frangi 4/17/2026

One-shot learning for the complex dynamical behaviors of weakly nonlinear forced oscillators

MEv-SINDy: one-shot learning method inferring governing equations of weakly nonlinear forced oscillators from single time series.

Ax Steven A. Senczyszyn, Timothy C. Havens, Nathaniel Rice, Jason E. Summers, Benjamin D. Werner, Benjamin J. Schumeg 4/17/2026

RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning

RL-STPA framework adapting system-theoretic hazard analysis to identify safety issues in reinforcement learning deployments.

Ax Come Fiegel, Pierre Menard, Tadashi Kozuno, Michal Valko, Vianney Perchet 4/17/2026

Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier

Log-barrier method achieving optimal last-iterate convergence in zero-sum matrix games with bandit feedback.

Ax Nouhaila Innan, Antonello Rosato, Alberto Marchisio, Muhammad Shafique 4/17/2026

How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations

Controlled benchmark comparing classical and quantum-oriented node embeddings for graph neural network classification.

Ax Yury Gorishniy, Ivan Rubachev, Dmitrii Feoktistov, Artem Babenko 4/17/2026

Benchmarking Optimizers for MLPs in Tabular Deep Learning

Systematic benchmark of optimizers beyond AdamW for tabular deep learning MLPs on supervised learning tasks.

Ax Muhammad Zeeshan Karamat, Sadman Saif, Christiana Chamon Garcia 4/17/2026

BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs

BitFlipScope: framework for localizing and recovering bit-flip hardware faults in LLM parameters affecting safety.

Ax Domonkos Varga 4/17/2026

Can Large Language Models Detect Methodological Flaws? Evidence from Gesture Recognition for UAV-Based Rescue Operation Based on Deep Learning

LLMs as analytical agents detecting methodological flaws (data leakage) in published ML papers via case study.

Ax Yingxuan Wen 4/17/2026

Decoupling Scores and Text: The Politeness Principle in Peer Review

Analysis of ICLR peer review showing large gap between score-based (91%) and text-based (83%) acceptance prediction accuracy.

Ax Bryan Sanchez 4/17/2026

Correcting Suppressed Log-Probabilities in Language Models with Post-Transformer Adapters

Post-transformer adapter (786K params) corrects suppressed log-probabilities in aligned LLMs on politically sensitive topics.

Ax Abhinav Moudgil, Ningyuan Huang, Eeshan Gunesh Dhekane, Pau Rodr\'iguez, Luca Zappella, Federico Danieli 4/17/2026

Attention to Mamba: A Recipe for Cross-Architecture Distillation

Knowledge distillation approach enabling efficient training of State Space Models (Mamba) using pretrained Transformer models.

Ax Pu Cheng, Juncheng Liu, Yunshen Long 4/17/2026

PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data

PolyBench: multimodal benchmark testing LLM capabilities on live prediction market data combining news and order-book dynamics.

Ax Aizierjiang Aiersilan, Mohamad Koubeissi 4/17/2026

Neuro-Oracle: A Trajectory-Aware Agentic RAG Framework for Interpretable Epilepsy Surgical Prognosis

arXiv paper on Neuro-Oracle, a retrieval-augmented agentic framework for predicting epilepsy surgical outcomes using longitudinal MRI trajectory analysis.

Ax Jiacheng Liu, Xiaohan Zhao, Xinyi Shang, Zhiqiang Shen 4/17/2026

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

arXiv study analyzing Claude Code architecture and design space of agentic systems, comparing with OpenClaw, identifying five human values in agent design.

Ax Pramudita Satria Palar, Paul Saves, Muhammad Daffa Robani, Nicolas Verstaevel, Moncef Garouani, Julien Aligon, Koji Shimoyama, Joseph Morlier, Benoit Gaudou 4/17/2026

Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making

arXiv survey on explainable surrogate models for complex system simulations, examining interpretability in black-box computational models.

Ax Wangjie Gan, Miao Pan, Linbo Xi, Wenqi Zhang, Jintao Chen, Jianwei Yin, Xuhong Zhang 4/17/2026

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

arXiv paper on Group Advantage Fine-Tuning (GFT) for LLMs, unifying supervised fine-tuning with reinforcement learning through policy gradient analysis.

Ax Qianyu Chen, Shujian Yu 4/17/2026

Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay

Continual learning framework for brain disorder diagnosis from fMRI using generative replay on functional connectivity matrices.

Ax Behnaz Elhaminia, Catherine King, Jiaqi Lv, Lorraine Harper, Paul Moss, Owen Cain, Dimitrios Chanouzas, Shan E Ahmed Raza 4/17/2026

A deep learning framework for glomeruli segmentation with boundary attention

U-Net-based deep learning model with boundary attention for glomeruli segmentation in kidney tissue using pathology foundation models.

Ax Carri W. Chan, Yi Han, Hannah Li, Benjamin L. Ranard 4/17/2026

Deployment of AI-Assisted Interventions: Capacity Constraints and Noisy Compliance

Study of AI-assisted intervention deployment in healthcare/education with capacity constraints and imperfect user compliance.

Ax Kristian Holme, Jean Rabault, Ricardo Vinuesa, Mikael Mortensen 4/17/2026

Timescale Separation Enables Deep Reinforcement Learning Control of Rotating Detonation Engine Mode Transitions

Deep reinforcement learning for controlling rotating detonation engine mode transitions using timescale separation.

Ax Felipe Parodi, Jordan Matelsky, Melanie Segado 4/17/2026

Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers

Analysis of register tokens in DINO vision transformers, showing zero-ablation overestimates their importance using multiple controls.

Ax Mel Sohm, Charles Dezons, Sami Sellami, Oscar Ninou, Axel Pincon 4/17/2026

Improving Machine Learning Performance with Synthetic Augmentation

Analysis of synthetic data augmentation's effect on training distributions and bias-variance tradeoffs in financial machine learning.

Ax Jianghong Huang, Luping Ji, Weiwei Duan, Mao Ye 4/17/2026

H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection

Few-shot anomaly detection using vision-language models and heterogeneous hypergraphs for industrial and medical imaging.

Ax Yuxiang Wang, Hongyu Liu, Yijiang Xu, Qinke Ni, Li Wang, Wan Lin, Kunyu Feng, Dekun Chen, Xu Tan, Lei Wang, Jie Shi, Zhizheng Wu 4/17/2026

VoxSafeBench: Not Just What Is Said, but Who, How, and Where

Benchmark for evaluating safety of speech language models across speaker identity, acoustic style, and location contexts.

Ax Sazzadul Islam, Tasnim Tabassum, Hao Zheng 4/17/2026

VeriGraphi: A Multi-Agent Framework of Hierarchical RTL Generation for Large Hardware Designs

Multi-agent LLM framework using hierarchical reasoning to generate synthesizable Verilog for hardware designs, addressing context and hallucination issues.

Ax Sumit Mukherjee, Juan Shu, Nairwita Mazumder, Tate Kernell, Celena Wheeler, Shannon Hastings, Chris Sidey-Gibbons 4/17/2026

Retrieve, Then Classify: Corpus-Grounded Automation of Clinical Value Set Authoring

RAG-based approach using LLMs to automate clinical value set authoring by retrieving and classifying codes from standardized vocabularies.

Ax Seyun Bae, Seokhan Lee, Eunho Yang 4/17/2026

CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge

CURaTE: continual unlearning method for LLMs enabling real-time knowledge removal while preserving model utility.

Ax David Y. Y. Tan, Kellie Chin, Jingxian Zhang 4/17/2026

AgentGA: Evolving Code Solutions in Agent-Seed Space

AgentGA: genetic algorithm framework for evolving autonomous code-generation agents by optimizing agent seed.

Ax Jianhao Su, Zhanwei Wu, ShengTing Huang, Weidong Feng 4/17/2026

AIPC: Agent-Based Automation for AI Model Deployment with Qualcomm AI Runtime

AIPC: AI agent-driven automation system for edge model deployment targeting hardware-specific inference runtimes.

Ax Krti Tallam 4/17/2026

Layered Mutability: Continuity and Governance in Persistent Self-Modifying Agents

Framework for understanding mutable state layers in persistent LLM-based agents with self-modification capabilities.

Ax Seokwon Lee, Jaeyoung Sim, Sihyun Kim, Yuhsing Li, Yiwen Zhu, Kwanghyun Park 4/17/2026

RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems

RELOAD: reinforcement learning-based query optimizer for database systems with robust per-query performance.

Ax Runze Li, Hongyin Zhang, Junxi Jin, Qixin Zeng, Zifeng Zhuang, Yiqi Tang, Shangke Lyu, Donglin Wang 4/17/2026

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems

World-Value-Action model for vision-language-action embodied agents with implicit planning capabilities.

Ax Adrian Edin, Michel Kieffer, Mikael Johansson, Zheng Chen 4/17/2026

Exploiting Correlations in Federated Learning: Opportunities and Practical Limitations

Systematic classification and analysis of compression techniques exploiting correlations in federated learning.

Ax Yifan Zhao, Yuchen Yang, Matei Budiu, Sasa Misailovic 4/17/2026

Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels

Nautilus tensor compiler with automated scheduling for efficient GPU kernel generation from high-level specifications.

Ax Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, Michal Valko 4/17/2026

Best of both worlds: Stochastic & adversarial best-arm identification

Bandit best-arm identification algorithm robust to both stochastic and adversarial reward distributions.

Ax Subhodip Panda, Shubhada Agrawal 4/17/2026

Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards

Theoretical analysis of regret tail behavior in multi-armed bandit algorithms with stochastic rewards.

Ax Danae S\'anchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras, Desmond Elliott 4/17/2026

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

arXiv paper analyzing reasoning dynamics and visual-textual information integration in 18 vision-language models.

Ax Evaldas Vaiciukynas, Paulius Danenas, Linas Ablonskis, Algirdas Sukys, Edgaras Dambrauskas, Voldemaras Zitkus, Rita Butkiene, Rimantas Butleris 4/17/2026

Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task

arXiv paper evaluating multilingual text embedding models for hate speech detection across Lithuanian, Russian, and English.

Ax Aihua Li 4/17/2026

Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

arXiv paper proposing mixture-of-experts flow matching for faster language model inference while maintaining generation quality.

Ax Haochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu, Enyan Dai 4/17/2026

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization

arXiv paper on Route to Rome Attack, demonstrating black-box adversarial suffix attacks on cost-aware LLM routers.

Ax Naryeong Kim, Shin Yoo 4/17/2026

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap

arXiv paper on Atropos, optimizing cost-performance trade-offs for LLM-based agents using small models with early termination and model hotswapping.

Ax Chenghui Zheng, Garvesh Raskutti 4/17/2026