Isolater - Feed

Ax Aleksei Khalin, Ekaterina Zaychenkova, Aleksandr Yugay, Andrey Goncharov, Sergey Korchagin, Alexey Zaytsev, Egor Ershov 4/3/2026

Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling

Expert-guided uncertainty modeling for medical AI systems to improve reliability and enable human experts to prioritize high-risk diagnostic cases.

Ax Zihao Wu, Hongyao Tang, Yi Ma, Jiashun Liu, Yan Zheng, Jianye Hao 4/3/2026

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning

Theoretical analysis of plasticity loss in deep reinforcement learning due to non-stationarity, proposing sample weight decay mitigation technique.

Ax Yuya Ishikawa, Shu Tamano 4/3/2026

PAC-Bayesian Reward-Certified Outcome Weighted Learning

PAC-Bayesian framework for outcome weighted learning that incorporates reward uncertainty into policy selection with finite-sample guarantees.

Ax Ilan Gold, Felix Fischer, Lucas Arnoldt, F. Alexander Wolf, Fabian J. Theis 4/3/2026

annbatch unlocks terabyte-scale training of biological data in anndata

annbatch: Mini-batch loader for terabyte-scale biological data training in anndata format, addressing memory bottlenecks in ML pipelines for bioinformatics.

Ax Kang-Sin Choi 4/3/2026

Learn by Surprise, Commit by Proof

LSCP: Self-gated post-training framework for autonomous knowledge acquisition using self-generated Q&A chains and adaptive learning rates based on model conviction.

Ax Adrien Weihs, Hayden Schaeffer 4/3/2026

Generalization Bounds and Statistical Guarantees for Multi-Task and Multiple Operator Learning with MNO Networks

Statistical analysis of multi-task and multiple operator learning architectures with generalization bounds and theoretical guarantees.

Ax Yuejiang Liu, Fan Feng, Lingjing Kong, Weifeng Lu, Jinzhou Tang, Kun Zhang, Kevin Murphy, Chelsea Finn, Yilun Du 4/3/2026

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry

Self-improving world models using forward-inverse asymmetry to improve robustness across suboptimal actions for policy evaluation and planning.

Ax Rafael Pardinas, Ehsan Kamalloo, David Vazquez, Alexandre Drouin 4/3/2026

Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning

RL post-training framework for building general-purpose reasoning models across diverse domains with verifiable rewards, addressing multi-domain optimization challenges.

Ax Dongrui Wu 4/3/2026

Feature Weighting Improves Pool-Based Sequential Active Learning for Regression

Active learning method using feature weighting for regression tasks to optimize sample selection from unlabeled pools under budget constraints.

Ax Jaber Jaber, Osama Jaber 4/3/2026

Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation

ArXiv paper on dynamic weight generation for recursive transformers using input-conditioned LoRA modulation controller.

Ax Atul Kumar Sinha, Fran\c{c}ois Fleuret 4/3/2026

AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression

ArXiv paper on fast SVD-based compression for large language models without retraining, addressing distribution shifts.

Ax M. Lo Verso, C. Introini, E. Cervi, L. Savoldi, J. N. Kutz, A. Cammi 4/3/2026

Application of parametric Shallow Recurrent Decoder Network to magnetohydrodynamic flows in liquid metal blankets of fusion reactors

ArXiv paper applying shallow recurrent decoder networks to magnetohydrodynamic flow modeling in fusion reactors.

Ax Roel Hacking, Lisa Kusch, Koondanibha Mitra, Martijn Anthonissen, Wilbert IJzerman 4/3/2026

Neural network methods for two-dimensional finite-source reflector design

ArXiv paper using neural networks to solve inverse problem of designing reflectors for light distribution.

Ax Mayank Mayank, Bharanidhar Duraisamy, Florian Geiss 4/3/2026

LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications

ArXiv paper on graph attention network for multi-sensor object fusion and tracking in autonomous driving.

Ax Xuanfeng Zhou 4/3/2026

Universal Hypernetworks for Arbitrary Models

ArXiv paper introducing Universal Hypernetworks that generate weights for arbitrary model architectures using descriptors.

Ax Hao Zhu, Di Zhou, Donna Slonim 4/3/2026

Smoothing the Landscape: Causal Structure Learning via Diffusion Denoising Objectives

ArXiv paper applying diffusion denoising objectives to causal structure learning from observational data.

Ax Klemens Iten, Bruce Lee, Chenhao Li, Lenart Treven, Andreas Krause, Bhavya Sukhija 4/3/2026

Model-Based Reinforcement Learning for Control under Time-Varying Dynamics

ArXiv paper on model-based reinforcement learning for control systems with time-varying dynamics.

Ax Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen 4/3/2026

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

ArXiv paper on in-context agentic reinforcement learning enabling LLM agents to internalize skills at inference time.

Ax Tin Had\v{z}i Veljkovi\'c, Joshua Rosenthal, Ivor Lon\v{c}ari\'c, Jan-Willem van de Meent 4/3/2026

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

ArXiv paper on lightweight diffusion transformer for crystal structure generation using subatomic tokenization.

Ax Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song, Mao Zheng, Haiyun Guo, Dan Zhang, Jinqiao Wang, Tat-Seng Chua 4/3/2026

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

ArXiv paper unifying group-relative and self-distillation policy optimization for LLM post-training with improved credit assignment.

Ax Dimitrios Danopoulos, Enrico Lupi, Michael Kagan, Maurizio Pierini 4/3/2026

Taming the Exponential: A Fast Softmax Surrogate for Integer-Native Edge Inference

ArXiv paper proposing Head-Calibrated Clipped-Linear Softmax as efficient surrogate for attention softmax in edge inference.

Ax Torque Dandachi, Sophia Diggs-Galligan 4/3/2026

go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices

ArXiv paper on exact parameterization of doubly stochastic matrices for learned mixing in neural networks.

Ax Bangji Yang, Hongbo Ma, Jiajun Fan, Ge Liu 4/3/2026

Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning

Single-stage training paradigm for efficient LLM reasoning that reduces token consumption in chain-of-thought without degrading quality.

Ax Yuan Qiu, Wei Li, Wei Zhang, Yi Zhou, Fang Liu, Jianbiao Wang, Zhi Wei Seh 4/3/2026

Interpretable Battery Aging without Extra Tests via Neural-Assisted Physics-based Modelling

Neural-assisted physics-based model for interpretable battery aging prediction via 2D aging fingerprints without additional diagnostics.

Ax Wenjie Qiu, Zixin Wang, Hongyu Fang, Zeyuan Ma, Yue-Jiao Gong 4/3/2026

A Learning-Based Cooperative Coevolution Framework for Heterogeneous Large-Scale Global Optimization

Learning-based cooperative coevolution framework addressing heterogeneous large-scale global optimization via adaptive low-dimensional optimizers.

Ax Okan U\c{c}ar, Murat Kurt 4/3/2026

OkanNet: A Lightweight Deep Learning Architecture for Classification of Brain Tumor from MRI Images

Lightweight deep learning architecture for brain tumor classification from MRI images with comparative analysis of different approaches.

Ax Nathan Benjamin, A. Liam Fitzpatrick, Wei Li, Jesse Thaler 4/3/2026

Descending into the Modular Bootstrap

Machine learning optimization applied to solve modular bootstrap equations for exploring 2D conformal field theories.

Ax Hanbing Liang, Fujun Liu 4/3/2026

Macroscopic transport patterns of UAV traffic in 3D anisotropic wind fields: A constraint-preserving hybrid PINN-FVM approach

Physics-informed neural network and finite volume hybrid approach for modeling UAV traffic patterns in 3D anisotropic wind fields.

Ax Vojt\v{e}ch Stan\v{e}k, Martin Pere\v{s}\'ini, Luk\'a\v{s} Sekanina, Anton Firc, Kamil Malinka 4/3/2026

Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors

Evolutionary multi-objective optimization framework for fusing deepfake speech detectors to balance accuracy and system complexity using NSGA-II.

Ax Hanbing Liang, Ze Tao, Fujun Liu 4/3/2026

Bias Inheritance in Neural-Symbolic Discovery of Constitutive Closures Under Function-Class Mismatch

Neural-symbolic framework for discovering constitutive closures in nonlinear PDEs from spatiotemporal data while avoiding spurious physical recovery.

Ax Neo Christopher Chung, Maxim Laletin 4/3/2026

Regularizing Attention Scores with Bootstrapping

Research on regularizing attention scores in vision transformers using bootstrapping to improve interpretability and reduce noisy attention maps.

Ax Manoj Parmar 4/3/2026

Safety, Security, and Cognitive Risks in World Models

Analysis of safety, security, and cognitive risks in world models used for autonomous decision-making in robotics, autonomous vehicles, and agentic AI systems.

Ax Luana P. Queiroz, Icaro S. C. Bernardes, Ana M. Ribeiro, Bernardo M. Aguilera-Mercado, Idelfonso B. R. Nogueira 4/3/2026

VIANA: character Value-enhanced Intensity Assessment via domain-informed Neural Architecture

Neural architecture for predicting odorant intensity perception by combining graph convolutional networks with domain-informed design for molecular structure analysis.

Ax Daran Xu, Amirhossein Taghvaei 4/3/2026

Causal Optimal Coupling for Gaussian Input-Output Distributional Data

Mathematical study of optimal coupling in causal dynamical systems using Schrödinger Bridge framework for input-output distributional data.

Ax Andrea Maldonado, Christian Imenkamp, Hendrik Reiter, Thomas Seidl, Wilhelm Hasselbring, Martin Werner, Agnes Koschmider 4/3/2026

Know Your Streams: On the Conceptualization, Characterization, and Generation of Intentional Event Streams

Framework for conceptualizing and generating intentional event streams to evaluate stream processing and mining algorithms.

Ax Georgiy A. Bondar, Abigail Eisenklam, Yifan Cai, Robert Gifford, Tushar Sial, Linh Thi Xuan Phan, Abhishek Halder 4/3/2026

Generative Profiling for Soft Real-Time Systems and its Applications to Resource Allocation

Generative approach for characterizing task timing in real-time systems across varying hardware resource contexts.

Ax Khalid Adnan Alsayed 4/3/2026

When AI Gets it Wong: Reliability and Risk in AI-Assisted Medication Decision Systems

Study of reliability gaps in AI-assisted medication systems, highlighting risks in healthcare decision support.

Ax Yakun Wang, Min Chen, Zeguan Wu, Junyu Liu, Sitao Zhang, Zhenwen Shao 4/3/2026

Infeasibility Aware Large Language Models for Combinatorial Optimization

Framework combining LLMs with infeasibility detection for NP-hard combinatorial optimization problems.

Ax Scott Xu, Dian Chen, Kelvin Wong, Chris Zhang, Kion Fallah, Raquel Urtasun 4/3/2026

Efficient Equivariant Transformer for Self-Driving Agent Modeling

Equivariant transformer architecture for modeling agent behaviors in autonomous driving with SE(2) symmetry.

Ax Zhehang Du, Weijie Su 4/3/2026

The Newton-Muon Optimizer

New optimizer deriving design principles from Muon, improving LLM training efficiency through surrogate model analysis.

Ax Yunbei Zhang, Chengyi Cai, Feng Liu, Jihun Hamm 4/3/2026

Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation

Method for efficiently adapting closed-box LLM APIs to target tasks by priming followed by local optimization.

Ax Matthew Loftus 4/3/2026

The topological gap at criticality: scaling exponent d + {\eta}, universality, and scope

Theoretical physics study of topological gaps in spin models and critical phenomena using persistent homology.

Ax Tareq Aldirawi, Yun Li, Wenge Guo 4/3/2026

Non-monotonicity in Conformal Risk Control

Research on conformal risk control under non-monotonic loss functions for distribution-free prediction guarantees.

Ax Smriti Jha, Matteo Paltenghi, Chandra Maddila, Vijayaraghavan Murali, Shubham Ugare, Satish Chandra 4/3/2026

ProdCodeBench: A Production-Derived Benchmark for Evaluating AI Coding Agents

Benchmark dataset for evaluating AI coding agents based on production workloads, addressing language distribution and codebase structure gaps.

Ax Yiming Fan (The Ohio State University), Jun Yeon Won (The Ohio State University), Ding Zhu (The Ohio State University), Melih Sirlanci (The Ohio State University), Mahdi Khalili (The Ohio State University), Carter Yagemann (The Ohio State University) 4/3/2026