Ax Elsa Cardoso-Bihlo, Alex Bihlo 24d ago

A solver-in-the-loop framework for end-to-end differentiable coastal hydrodynamics

AegirJAX: fully differentiable hydrodynamic solver for coastal wave propagation and inverse problems using end-to-end differentiable computing.

Ax Carlos Caetano, Camila Laranjeira, Clara Ernesto, Artur Barros, Jo\~ao Macedo, Leo S. F. Ribeiro, Jefersson A. dos Santos, Sandra Avila 24d ago

CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research

Privacy-preserving structural dataset (CSA-Graphs) for child sexual abuse imagery classification research without releasing original images.

Ax Qichen Wang, Keyu Li, Ozan Alp Topal, \"Ozlem Tugfe Demir, Mustafa Ozger, Cicek Cavdar 24d ago

Energy Saving for Cell-Free Massive MIMO Networks: A Multi-Agent Deep Reinforcement Learning Approach

Multi-agent deep reinforcement learning for energy optimization in cell-free massive MIMO networks. Distributed antenna reconfiguration and sleep mode selection.

Ax Ryan Lingo, Rajeev Chhajer 24d ago

Dynamic Context Evolution for Scalable Synthetic Data Generation

Introduces Dynamic Context Evolution (DCE) to address cross-batch mode collapse in LLMs, where repeated prompting causes output repetitiveness. Proposes principled framework beyond ad hoc deduplication.

Ax Yu Li, Sizhe Tang, Tian Lan 24d ago

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization

T-STAR: tree-structured reinforcement learning for multi-turn LLM agents with self-rectification and grafting for sparse reward optimization.

Ax Robert Zimmermann, Thomas Norrenbrock, Bodo Rosenhahn 24d ago

DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification

DINO-QPM: lightweight interpretability adapter converting DINOv2 visual foundation model features into human-interpretable representations.

Ax Muhammad Fahim Tajwar, Arthur Wuhrlin, Bhojan Anand 24d ago

Splats under Pressure: Exploring Performance-Energy Trade-offs in Real-Time 3D Gaussian Splatting under Constrained GPU Budgets

Performance-energy trade-off analysis for real-time 3D Gaussian Splatting on edge GPUs with controlled computational budgets.

Ax Rafi Ahamed, Sidratul Moon Nafsin, Md Abir Rahman, Tasnia Tarannum Roza, Munaia Jannat Easha, Abu Raihan 24d ago

TeaLeafVision: An Explainable and Robust Deep Learning Framework for Tea Leaf Disease Classification

Deep learning framework for tea leaf disease classification using CNN models with explainability and robustness evaluation.

Ax Nathan Lambert, Florian Brand 24d ago

The ATOM Report: Measuring the Open Language Model Ecosystem

ATOM Report: comprehensive adoption analysis of ~1.5K open language models showing Chinese models surpassing US counterparts in 2025.

Ax Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen 24d ago

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

TraceSafe-Bench: first comprehensive benchmark evaluating LLM guardrails efficacy in multi-step tool-use agent trajectories.

Ax Huidong Ma, Xinyan Shi, Hui Sun, Xiaofei Yue, Xiaoguang Liu, Gang Wang, Wentong Cai 24d ago

Efficient Learned Data Compression via Dual-Stream Feature Decoupling

Efficient learned data compression via dual-stream feature decoupling to balance probability modeling with system latency.

Ax Kirill Brilliantov, Etienne Bamas, Emmanuel Abb\'e 24d ago

$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture

k-server-bench: automated mathematical discovery challenge for finding potential functions in the k-server conjecture.

Ax Icaro Re Depaolini, Uri Hasson 24d ago

Non-identifiability of Explanations from Model Behavior in Deep Networks of Image Authenticity Judgments

Study on robustness of attribution heatmap explanations in deep networks trained to predict human image authenticity judgments.

Ax Robert Allison, Tomasz Maciazek, Anthony Stephenson 24d ago

The Theory and Practice of Highly Scalable Gaussian Process Regression with Nearest Neighbours

Theory and practice of scalable Gaussian process regression using nearest neighbours for massive dataset applications.

Ax Nusrat Sultana, Abdullah Muhammad Moosa, Kazi Afzalur Rahman, Sajal Chandra Banik 24d ago

A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering

Systematic study analyzing impact of retrieval pipeline components on RAG-based medical question answering systems with LLMs.

Ax Luca Pennati, Andong Hu, Ivy Peng, Lukas M\"ullender, Stefano Markidis 24d ago

Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACS

Integration of DeePMD-kit neural network potentials into GROMACS for multi-GPU accelerated molecular dynamics simulations.

Ax Fizza Rubab, Yiying Tong, Arun Ross 24d ago

Are Face Embeddings Compatible Across Deep Neural Network Models?

Study comparing compatibility of face embeddings across different deep neural network models for biometric applications.

Ax Timothy K Johnsen, Marco Levorato 24d ago

CADENCE: Context-Adaptive Depth Estimation for Navigation and Computational Efficiency

CADENCE: adaptive depth estimation system for autonomous vehicles that dynamically scales neural network complexity for embedded processors.

Ax Huaiyuan Qin, Muli Yang, Gabriel James Goenawan, Kai Wang, Zheng Wang, Peng Hu, Xi Peng, Hongyuan Zhu 24d ago

Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment

AlignPrune: noise-robust dynamic data pruning method using loss trajectory alignment to preserve clean samples under label noise.

Ax Artemy Rubtsov, Sergey Samsonov, Vladimir Ulyanov, Alexey Naumov 24d ago

Gaussian Approximation for Asynchronous Q-learning

Convergence rate analysis for asynchronous Q-learning with polynomial stepsize under high-dimensional central limit theorem conditions.

Ax Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao 24d ago

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

Personalized RewardBench: novel benchmark for evaluating reward models' ability to capture individual user preferences in LLM alignment.

Ax Roberto Vercellino (National Laboratory of the Rockies), Jared Willard (National Laboratory of the Rockies), Gustavo Campos (National Laboratory of the Rockies), Weslley da Silva Pereira (National Laboratory of the Rockies), Olivia Hull (National Laboratory of the Rockies), Matthew Selensky (National Laboratory of the Rockies), Juliane Mueller (National Laboratory of the Rockies) 24d ago

Measurement of Generative AI Workload Power Profiles for Whole-Facility Data Center Infrastructure Planning

Methodology for measuring generative AI power consumption across data centers to address proprietary data gaps and infrastructure planning.

Ax Shaowei Liu, Xuanchi Ren, Tianchang Shen, Huan Ling, Saurabh Gupta, Shenlong Wang, Sanja Fidler, Jun Gao 24d ago

MoRight: Motion Control Done Right

arXiv paper on motion-controlled video generation with disentangled control and motion causality for physical scene dynamics.

Ax Ziqiao Ma, Xueyang Yu, Haoyu Zhen, Yuncong Yang, Joyce Chai, Chuang Gan 24d ago

Fast Spatial Memory with Elastic Test-Time Training

Elastic Test-Time Training method addressing catastrophic forgetting in long-context 3D reconstruction with plastic inference-time updates.

Ax Eduardo C. Garrido-Merch\'an, \'Alvaro L\'opez L\'opez 24d ago

An Automated Survey of Generative Artificial Intelligence: Large Language Models, Architectures, Protocols, and Applications

Comprehensive arXiv survey of generative AI covering LLM architectures, deployment protocols, and applications as of early 2026.

Ax Chris Kolb, Christian L. M\"uller, Bernd Bischl, David R\"ugamer 24d ago

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization

Framework for smooth optimization of explicitly regularized sparse objectives via Hadamard overparametrization, enabling gradient-descent compatible solvers.

Ax Florian E. Dorner, Moritz Hardt 24d ago

Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget

Theoretical analysis showing single labels on more samples outperforms multiple labels per sample for binary classifier comparison under noisy label budgets.

Ax Abdulla Al-Subaiey, Mohammed Al-Thani, Naser Abdullah Alam, Kaniz Fatema Antora, Amith Khandakar, SM Ashfaq Uz Zaman 24d ago

Novel Interpretable and Robust Web-based AI Platform for Phishing Email Detection

Web-based ML platform for phishing email detection achieving F1=0.99 on public dataset with interpretability and robustness for deployment.

Ax Run He, Kai Tong, Di Fang, Han Sun, Ziqian Zeng, Haoran Li, Tianyi Chen, Huiping Zhuang 24d ago

AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models

Analytic federated learning (AFL) paradigm enabling closed-form solutions for federated learning with pre-trained models in single-round training.

Ax Mingze Ni, Wei Liu 24d ago

SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification

SleepNet and DreamNet: deep learning models for visual classification via feature enrichment and reconstruction with pre-trained encoders.

Ax Chin-Chia Michael Yeh, Audrey Der, Uday Singh Saini, Vivian Lai, Yan Zheng, Junpeng Wang, Xin Dai, Zhongfang Zhuang, Yujie Fan, Huiyuan Chen, Prince Osei Aboagye, Liang Wang, Wei Zhang, Eamonn Keogh 24d ago

Matrix Profile for Anomaly Detection on Multidimensional Time Series

Matrix Profile extension for anomaly detection in multidimensional time series from real-world applications like sensor monitoring.

Ax Taisuke Kobayashi 24d ago

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning

DROP: distributional reinforcement learning framework with asymmetric learning rates modeling optimistic/pessimistic dopamine neuron behavior.

Ax Zihao Zhao, Yuchen Yang, Anjalie Field, Yinzhi Cao 24d ago

Pseudo-Probability Unlearning: Efficient and Privacy-Preserving Machine Unlearning

Pseudo-probability unlearning method for efficient privacy-preserving machine unlearning with reduced computational overhead and residual information.

Ax Markus Gambietz, Eva Dorschky, Altan Akat, Marcel Sch\"ockel, J\"org Miehling, Anne D. Koelewijn 24d ago

SSPINNpose: A Self-Supervised PINN for Inertial Pose and Dynamics Estimation

Self-supervised physics-informed neural network for real-time human pose and dynamics estimation from sparse IMU sensor configurations.

Ax Meihua Dang, Jiaqi Han, Minkai Xu, Kai Xu, Akash Srivastava, Stefano Ermon 24d ago

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement

Inference-time scaling method for discrete diffusion language models via trajectory refinement without retraining for reward optimization.

Ax Yixuan Zhang, Jinhao Sheng, Wenxin Zhang, Quyu Kong, Feng Zhou 24d ago

Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling

Negative Binomial VAE extension with discrete count-based latents for improved biological plausibility over continuous VAE representations.

Ax Lin-Han Jia, Si-Yu Han, Wen-Chao Hu, Jie-Jing Shao, Wen-Da Wei, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li 24d ago

Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning

Method for quantitatively estimating target task performance from unsupervised pretext tasks in semi/self-supervised learning before full training.

Ax Ze Tao, Hanxuan Wang, Fujun Liu 24d ago

LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks

LNN-PINN: physics-informed neural network framework with liquid residual gating for improved predictive accuracy on complex PDE problems.

Ax Amir Rezaei Balef, Katharina Eggensperger 24d ago

In-Context Decision Making for Optimizing Complex AutoML Pipelines

In-context learning approach for AutoML pipeline optimization beyond hyperparameter tuning, incorporating fine-tuning and ensembling techniques.

Ax Zuzanna Gawrysiak, Krzysztof Krawiec 24d ago

Physics-Informed Spectral Modeling for Hyperspectral Imaging

PhISM: physics-informed deep learning architecture for unsupervised hyperspectral imaging using continuous basis functions for interpretable latent representations.

Ax Zhiyuan Huang, Jiahao Chen, Bing Su 24d ago

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

LoFT method for long-tailed semi-supervised learning using foundation models with parameter-efficient fine-tuning to improve pseudo-label quality.

Ax David P. Morton, Oscar Dowson, Bernardo K. Pagnoncelli 24d ago

MDP modeling for multi-stage stochastic programs

MDP modeling framework extending policy graphs for multi-stage stochastic programs with decision-dependent uncertainty and statistical learning.

Ax Xi Wang, James McInerney, Lequn Wang, Nathan Kallus 24d ago

Entropy After </Think> for reasoning model early exiting

Technique for detecting when reasoning LLMs overthink by analyzing entropy after chain-of-thought to enable early exiting.

Ax Soohaeng Yoo Willow, Tae Hyeon Park, Gi Beom Sim, Sung Wook Moon, Seung Kyu Min, D. ChangMo Yang, Hyun Woo Kim, Juho Lee, Chang Woo Myung 24d ago

Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing

Bayesian machine learning potentials for molecular simulations with uncertainty quantification using equivariant message passing.

Ax Yuezhu Xu, S. Sivaranjani 24d ago

ECLipsE-Gen-Local: Efficient Compositional Local Lipschitz Estimates for Deep Neural Networks

Method for efficiently computing Lipschitz constant estimates for neural networks using local information to improve robustness certification.

Ax Max Hopkins, Russell Impagliazzo, Christopher Ye 24d ago

Approximate Replicability in Learning

Approximate replicability framework for machine learning algorithms that remain stable under input resampling.

Ax Iv\'an Ojeda-Ruiz, Young Ju Lee, Malcolm Dickens, Leonardo Cambisaca 24d ago

Alternatives to the Laplacian for Scalable Spectral Clustering with Group Fairness Constraints

Spectral clustering alternatives to Laplacian with group fairness constraints for equitable cluster representation.

Ax Zhichao Wang 24d ago

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA

GIFT unifies GRPO, DPO, and UNA in reinforcement learning framework for LLM alignment combining group-relative sampling with implicit preference learning.

Ax Qingyue Zhang, Chang Chu, Tianren Peng, Qi Li, Xiangyang Luo, Zhihao Jiang, Shao-Lun Huang 24d ago

LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis

LoRA-DA provides data-aware initialization for low-rank adaptation via theoretical framework and asymptotic analysis for parameter-efficient fine-tuning.

Ax Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou 24d ago

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism

Nirvana specialized generalist model with task-aware memory mechanism for domain adaptation while preserving broad LLM capabilities.