Isolater - Feed

Ax Patrick Wilhelm, Odej Kao 3/10/2026

Revisiting Gradient Staleness: Evaluating Distance Metrics for Asynchronous Federated Learning Aggregation

Evaluation of distance metrics for staleness measurement in asynchronous federated learning aggregation methods.

Ax Dai Shi, Luke Thompson, Andi Han, Peiyan Hu, Junbin Gao, Jos\'e Miguel Hern\'andez-Lobato 3/10/2026

Wiener Chaos Expansion based Neural Operator for Singular Stochastic Partial Differential Equations

Wiener Chaos Expansion-based neural operator using FiLM for solving singular stochastic partial differential equations.

Ax Chang Li, Tshihao Tsu, Yaren Zhang, Chao Xue, Xiaodong He 3/10/2026

Fibration Policy Optimization

Fibration Policy Optimization introduces APC-Obj for training heterogeneous LLM systems with multi-scale hierarchical stability control.

Ax Prakash Kumbhakar, Shrey Srivastava, Haroon R Lone 3/10/2026

FedPrism: Adaptive Personalized Federated Learning under Non-IID Data

FedPrism framework for federated learning with non-IID data, using adaptive personalization strategies under statistical heterogeneity.

Ax Yuxiang Zhang, Enyan Dai 3/10/2026

SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning

SCL-GNN addresses spurious correlations in graph neural networks to improve generalization across diverse graph tasks.

Ax Chaewon Moon, Dongkuk Si, Chulhee Yun 3/10/2026

Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization

Theoretical analysis of implicit bias in Sharpness-Aware Minimization showing depth-dependent behavior in linear networks diverges from gradient descent.

Ax Shubham Aggarwal, Lokendra Kumar 3/10/2026

Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers

Replaces dense attention output projections with fixed Walsh Hadamard Transform to reduce parameters and inference cost in transformer models.

Ax Marcin Kostrzewa, Krzysztof Galus, Maciej Zi\k{e}ba 3/10/2026

Towards plausibility in time series counterfactual explanations

Method for generating plausible counterfactual explanations for time series classification using soft-DTW alignment with k-nearest neighbors.

Ax Gustavo A. Dorrego 3/10/2026

Beyond the Markovian Assumption: Robust Optimization via Fractional Weyl Integrals in Imbalanced Data

Novel optimization algorithm using fractional calculus to handle noisy weight updates and improve gradient descent performance on imbalanced datasets.

Ax Dongsu Lee, Daehee Lee, Amy Zhang 3/10/2026

A Recipe for Stable Offline Multi-agent Reinforcement Learning

Stable offline multi-agent reinforcement learning approach addressing instability in non-linear value decomposition for MARL from batched data.

Ax Daniil Karzanov, Marcin Detyniecki 3/10/2026

Geometrically Constrained Outlier Synthesis

Training-time regularization method generating virtual outliers in feature space to improve out-of-distribution robustness in image classification networks.

Ax Jes\'us S\'anchez Ochoa, Enrique Tom\'as Mart\'inez Beltr\'an, Alberto Huertas Celdr\'an 3/10/2026

SYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence Encoding

SYNAPSE framework for neuron-level interpretability and perturbation analysis in sequence encoding models to improve transparency and robustness.

Ax Adrian Garcia-Casta\~neda, Jon Irureta, Jon Imaz, Aizea Lojo 3/10/2026

Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning

Dynamic scaling framework for class incremental learning that adaptively manages architectural growth and memory overhead while preventing catastrophic forgetting.

Ax Dongfang Li, Zixuan Liu, Gang Lin, Baotian Hu, Min Zhang 3/10/2026

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing

LycheeCluster method for efficient long-context LLM inference using structure-aware chunking and hierarchical KV cache indexing to reduce attention complexity.

Ax Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi 3/10/2026

Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck

Recasts efficient chain-of-thought prompting in LLMs as compression problem under Information Bottleneck principle to reduce token usage and inference cost.

Ax Eric Parish, Anthony Gruber, Patrick Blonigan, Irina Tezaur 3/10/2026

NN-OpInf: an operator inference approach using structure-preserving composable neural networks

Structure-preserving neural network operator inference framework for non-intrusive reduced-order modeling of dynamical systems from snapshot data.

Ax Paul Hofman, Timo L\"ohr, Maximilian Muschalik, Yusuf Sale, Eyke H\"ullermeier 3/10/2026

Efficient Credal Prediction through Decalibration

Framework for efficient credal prediction using decalibration to represent epistemic uncertainty in safety-critical machine learning applications.

Ax Prajit T Rajendran, Fabio Arnez, Huascar Espinoza, Agnes Delaborde, Chokri Mraidha 3/10/2026

Oracle-Guided Soft Shielding for Safe Move Prediction in Chess

Safe move prediction in chess using oracle-guided soft shielding to combine imitation and reinforcement learning for reducing safety-critical errors.

Ax Swetha Ganesh, Vaneet Aggarwal 3/10/2026

Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning

Novel approach to multi-objective reinforcement learning using concave scalarization to optimize nonlinear utility functions over multiple reward objectives.

Ax Songyang Chen, Youfang Lin, Yu Liu, Shuai Zheng, Lei Zou 3/10/2026

Towards Effective and Efficient Graph Alignment without Supervision

Unsupervised graph alignment method using deep learning and optimal transport to find node correspondence across different graphs without labeled pairs.

Ax Tommaso Giorgi, Pierriccardo Olivieri, Keyue Jiang, Laura Toni, Matteo Papini 3/10/2026

Impact of Connectivity on Laplacian Representations in Reinforcement Learning

Research on learning compact state representations in reinforcement learning using Laplacian eigenvectors to address dimensionality challenges in large-scale RL problems.

Ax Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh 3/10/2026

Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates

Drift2Act controller for handling distribution drift in deployed ML systems with budgeted interventions and online risk certificates.

Ax Andr\'es Ortiz, Nicol\'as J. Gallego-Molina, Carmen Jim\'enez-Mesa, Juan M. G\'orriz, Javier Ram\'irez 3/10/2026

DualFlexKAN: Dual-stage Kolmogorov-Arnold Networks with Independent Function Control

DualFlexKAN extends Kolmogorov-Arnold Networks with learnable dual-stage functions to address quadratic parameter scaling and architectural limitations.

Ax Riccardo De Monte, Matteo Cederle, Gian Antonio Susto 3/10/2026

Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control

Streaming deep reinforcement learning method for continuous control on resource-limited hardware using online updates without replay buffers.

Ax Federico Giannini, Sandro D'Andrea, Emanuele Della Valle 3/10/2026

Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence

MAGIC Net approach for streaming continual learning that combines architectural strategies with RNNs to handle concept drift and temporal dependence.

Ax Dyah Adila, Hanna Mazzawi, Benoit Dherin, Xavier Gonzalvo 3/10/2026

Grow, Don't Overwrite: Fine-tuning Without Forgetting

Function-preserving expansion method for fine-tuning pre-trained models without catastrophic forgetting by replicating model capacity.

Ax Fenix W. Huang, Henning S. Mortveit, Christian M. Reidys 3/10/2026

Divide and Predict: An Architecture for Input Space Partitioning and Enhanced Accuracy

Input space partitioning architecture using data heterogeneity measures to improve supervised learning accuracy on mixture-of-distributions data.

Ax Andrzej Cichocki, Piergiulio Tempesta 3/10/2026

Group Entropies and Mirror Duality: A Class of Flexible Mirror Descent Updates for Machine Learning

Theoretical framework connecting group theory and group entropies to mirror descent optimization algorithms for flexible machine learning updates.

Ax Bingxiang He, Yuxin Zuo, Zeyuan Liu, Shangziqi Zhao, Zixuan Fu, Junlin Yang, Cheng Qian, Kaiyan Zhang, Yuchen Fan, Ganqu Cui, Xiusi Chen, Youbang Sun, Xingtai Lv, Xuekai Zhu, Li Sheng, Ran Li, Huan-ang Gao, Yuchen Zhang, Bowen Zhou, Zhiyuan Liu, Ning Ding 3/10/2026

How Far Can Unsupervised RLVR Scale LLM Training?

Comprehensive analysis of unsupervised reinforcement learning with verifiable rewards for scaling LLM training without supervision bottleneck, including taxonomy and experiments.

Ax Yiannis Papageorgiou, Yannis Thomas, Ramin Khalili, Iordanis Koutsopoulos 3/10/2026

Split Federated Learning Architectures for High-Accuracy and Low-Delay Model Training

Split Federated Learning architecture optimization for improving training accuracy and reducing delay in distributed ML model training.

Ax Azul Garza, Ren\'ee Rosillo, Rodrigo Mendoza-Smith, David Salinas, Andrew Robert Williams, Arjun Ashok, Mononito Goswami, Jos\'e Mart\'in Ju\'arez 3/10/2026

Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting

Impermanent benchmark for evaluating temporal generalization in time-series forecasting models, addressing data contamination issues in foundation models.

Ax Fei Wang, Jiangnan Yang, Junjie Chen, Yuxin Liu, Kun Li, Yanyan Wei, Dan Guo, Meng Wang 3/10/2026

XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being

XInsight multi-agent framework for LLM-driven psychological counseling support with stage-consistent workflow aligned to therapeutic practices.

Ax Jonas Rohweder, Subhabrata Dutta, Iryna Gurevych 3/10/2026

Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale

Research on unified understanding of phenomena in Transformer language models through hierarchical latent structures in data generation processes.

Ax Nikita Sorokin, Ivan Sedykh, Valentin Malykh 3/10/2026

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation

Hierarchical Embedding Fusion method for retrieval-augmented code generation that compresses repositories into dense vector hierarchies to reduce inference cost and context noise.

Ax Siyuan Wang, Lei Lei, Pranav Maheshwari, Sam Bellefeuille, Kan Zheng, Dusit Niyato 3/10/2026

Multi-Agent DRL for V2X Resource Allocation: Disentangling Challenges and Benchmarking Solutions

Multi-agent deep reinforcement learning for radio resource allocation in V2X networks, addressing challenges like non-stationarity, coordination, and partial observability.

Ax Sourav Panda, Shreyash Kale, Tanmay Ambadkar, Abhinav Verma, Jonathan Dodge 3/10/2026

Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research

Open-source StarCraft II benchmark for reinforcement learning research with accessible compute requirements and curriculum design capabilities.

Ax Fali Wang, Chenglin Weng, Xianren Zhang, Siyuan Hong, Hui Liu, Suhang Wang 3/10/2026