Academic

Academic · 1 min

DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learning

arXiv:2603.19314v1 Announce Type: new Abstract: In the modern financial system, combating money laundering is a critical challenge complicated by data privacy concerns and increasingly complex …

Renuga Kanagavelu, Manjil Nepal, Ning Peiyan, Cai Kangning, Xu Jiming, Fei Gao, Yong Liu, Goh Siow Mong Rick, Qingsong Wei

41 views Mar 23

Academic · 1 min

MSNet and LS-Net: Scalable Multi-Scale Multi-Representation Networks for Time Series Classification

arXiv:2603.19315v1 Announce Type: new Abstract: Time series classification (TSC) performance depends not only on architectural design but also on the diversity of input representations. In …

Celal Alag\"oz, Mehmet Kurnaz, Farhan Aadil

4 views Mar 23

Academic · 1 min

Ternary Gamma Semirings: From Neural Implementation to Categorical Foundations

arXiv:2603.19317v1 Announce Type: new Abstract: This paper establishes a theoretical framework connecting neural network learning with abstract algebraic structures. We first present a minimal counterexample …

Ruoqi Sun

5 views Mar 23

Academic · 1 min

A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints

arXiv:2603.19322v1 Announce Type: new Abstract: While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete …

Yikun Wang, Yang Li, Yik-Chung Wu, Rui Zhang

39 views Mar 23

Academic · 1 min

Target Concept Tuning Improves Extreme Weather Forecasting

arXiv:2603.19325v1 Announce Type: new Abstract: Deep learning models for meteorological forecasting often fail in rare but high-impact events such as typhoons, where relevant data is …

Shijie Ren, Xinyue Gu, Ziheng Peng, Haifan Zhang, Peisong Niu, Bo Wu, Xiting Wang, Liang Sun, Jirong Wen

5 views Mar 23

Academic · 1 min

FalconBC: Flow matching for Amortized inference of Latent-CONditioned physiologic Boundary Conditions

arXiv:2603.19331v1 Announce Type: new Abstract: Boundary condition tuning is a fundamental step in patient-specific cardiovascular modeling. Despite an increase in offline training cost, recent methods …

Chloe H. Choi, Alison L. Marsden, Daniele E. Schiavazzi

4 views Mar 23

Academic · 1 min

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions

arXiv:2603.19335v1 Announce Type: new Abstract: Post-training alignment has produced dozens of competing algorithms -- DPO, SimPO, KTO, GRPO, and others -- yet practitioners lack controlled …

Xiaoyi Li

6 views Mar 23

Academic · 1 min

DAPA: Distribution Aware Piecewise Activation Functions for On-Device Transformer Inference and Training

arXiv:2603.19338v1 Announce Type: new Abstract: Non-linear activation functions play a pivotal role in on-device inference and training, as they not only consume substantial hardware resources …

Maoyang Xiang, Bo Wang

5 views Mar 23

Academic · 1 min

Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons

arXiv:2603.19344v1 Announce Type: new Abstract: Weighted summation has remained the default input aggregation mechanism in artificial neurons since the earliest neural network models. While computationally …

Berke Deniz Bozyigit

5 views Mar 23

Academic · 1 min

Anatomical Heterogeneity in Transformer Language Models

arXiv:2603.19348v1 Announce Type: new Abstract: Current transformer language models are trained with uniform computational budgets across all layers, implicitly assuming layer homogeneity. We challenge this …

Tomasz Wietrzykowski

6 views Mar 23

Academic · 1 min

A Mathematical Theory of Understanding

arXiv:2603.19349v1 Announce Type: new Abstract: Generative AI has transformed the economics of information production, making explanations, proofs, examples, and analyses available at very low cost. …

Bahar Ta\c{s}kesen

22 views Mar 23

Academic · 1 min

Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation

arXiv:2603.19360v1 Announce Type: new Abstract: Current auto-regressive (AR) LLMs, diffusion-based text/image generative models, and recent flow matching (FM) algorithms are capable of generating premium quality …

Minyoung Kim

4 views Mar 23

DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learning

MSNet and LS-Net: Scalable Multi-Scale Multi-Representation Networks for Time Series Classification

Ternary Gamma Semirings: From Neural Implementation to Categorical Foundations

A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints

Target Concept Tuning Improves Extreme Weather Forecasting

FalconBC: Flow matching for Amortized inference of Latent-CONditioned physiologic Boundary Conditions

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions

DAPA: Distribution Aware Piecewise Activation Functions for On-Device Transformer Inference and Training

Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons

Anatomical Heterogeneity in Transformer Language Models

A Mathematical Theory of Understanding

Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation

JCG, PC

HSOLLC Co., Ltd.