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

EXHIB: A Benchmark for Realistic and Diverse Evaluation of Function Similarity in the Wild

EXHIB benchmark for binary function similarity detection supporting vulnerability analysis and malware classification.

Ax Abdelrahman Abouzeid (Georgia Institute of Technology) 4/3/2026

Does Your Optimizer Care How You Normalize? Normalization-Optimizer Coupling in LLM Training

Study of interactions between normalization methods and optimizers in LLM training at 1B parameters.

Ax Zhihuan Wei, Xinhang Chen, Danyang Han, Yang Hu, Jie Liu, Xuewen Miao, Guijiang Li 4/3/2026

LiteInception: A Lightweight and Interpretable Deep Learning Framework for General Aviation Fault Diagnosis

LiteInception: lightweight interpretable deep learning framework for fault diagnosis on edge devices.

Ax Linyang He, Qiyao Yu, Hanze Dong, Baohao Liao, Xinxing Xu, Micah Goldblum, Jiang Bian, Nima Mesgarani 4/3/2026

LiveMathematicianBench: A Live Benchmark for Mathematician-Level Reasoning with Proof Sketches

LiveMathematicianBench: benchmark for evaluating LLM mathematical reasoning capabilities with proof sketches.

Ax Jung-hun Kim, Vianney Perchet 4/3/2026

Learning in Prophet Inequalities with Noisy Observations

Prophet inequality problem with noisy observations and unknown reward distributions using linear models.

Ax Yaxin Luo, Zhiqiang Shen 4/3/2026

Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks

Study on language pre-training bias improving performance on general vision tasks through cross-modality transfer.

Ax Jamie S. J. Stirling, Noura Al-Moubayed, Hubert P. H. Shum 4/3/2026

Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images

Analysis of permutation-invariant discrete representation learning for spatially aligned images using vector quantization.

Ax George Sebastian, Philipp Berthold, Bianca Forkel, Leon Pohl, Mirko Maehlisch 4/3/2026

Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Data via Visibility-Aware Cross-Modal Supervision

Learning spatial structure from automotive radar pre-beamforming data using cross-modal supervision.

Ax Ga\"etan Hadjeres, Marc Ferras, Khaled Koutini, Benno Weck, Alexandre Bittar, Thomas Hummel, Zineb Lahrici, Hakim Missoum, Joan Serr\`a, Yuki Mitsufuji 4/3/2026

Woosh: A Sound Effects Foundation Model

Woosh: open-source sound effects foundation model from Sony AI with architecture, training details, and benchmarks.

Ax Isma\"il Baaj, Pierre Marquis 4/3/2026

Probabilistic classification from possibilistic data: computing Kullback-Leibler projection with a possibility distribution

Multi-class classification approach using possibilistic supervision and Kullback-Leibler projection.

Ax Dominique Pastor, Elsa Dupraz, Ismail Hbilou, Guillaume Ansel 4/3/2026

A Novel Theoretical Analysis for Clustering Heteroscedastic Gaussian Data without Knowledge of the Number of Clusters

Theoretical analysis for clustering heteroscedastic Gaussian data without prior knowledge of cluster count.

Ax Anatolij Zubow, Joana Angjo, Sigrid Dimce, Falko Dressler 4/3/2026

Physics-Informed Transformer for Multi-Band Channel Frequency Response Reconstruction

Physics-informed transformer for reconstructing wideband channel frequency response in multi-band wireless systems.

Ax Saja Al-Dabet, Sherzod Turaev, Nazar Zaki 4/3/2026

Abnormal Head Movements in Neurological Conditions: A Knowledge-Based Dataset with Application to Cervical Dystonia

NeuroPose-AHM dataset integrating kinematic measurements and clinical scores for neurological disorder diagnosis.

Ax Ayush Garg, Sophia Hager, Jacob Montiel, Aditya Tiwari, Michael Gentile, Zach Reavis, David Magnotti, Wayne Fullen 4/3/2026

RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

AWS system for automated generation of detection rules for web vulnerability identification from CVE data.

Ax Hugo Koubbi, Borjan Geshkovski, Philippe Rigollet 4/3/2026

Homogenized Transformers

Theoretical analysis of multi-head self-attention transformers using particle systems and homogenization limits.

Ax Antoine Saporta, Baptiste Callard, Corentin Dancette, Julien Khlaut, Charles Corbi\`ere, Leo Butsanets, Amaury Prat, Pierre Manceron 4/3/2026

Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

Curia-2 foundation model using self-supervised learning for medical imaging analysis on CT and MRI data.

Ax Xiaofei Song, Kerstin Eder, Jonathan Lawry, R. Eddie Wilson 4/3/2026

Systematic Analyses of Reinforcement Learning Controllers in Signalized Urban Corridors

Comparison of centralized and decentralized RL controllers for traffic signal control in urban corridor networks.

Ax Sebastian-Ion Nae, Radu Moldoveanu, Alexandra Stefania Ghita, Adina Magda Florea 4/3/2026

IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline

Multi-scene indoor dataset for human detection, segmentation, and tracking across campus locations with automated annotation pipeline.

Ax Yun Zhao, Alex S. L. Tse, Harry Zheng 4/3/2026

Reinforcement Learning for Speculative Trading under Exploratory Framework

Reinforcement learning approach for speculative trading formulated as sequential optimal stopping with Cox process-driven intensity controls.

Ax Soo Won Seo, KyungChae Lee, Hyungchan Cho, Taein Son, Nam Ik Cho, Jun Won Choi 4/3/2026

Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection

Mining instance-centric vision-language contexts for human-object interaction detection, leveraging VLMs to improve semantic understanding and contextual reasoning.