20 results for “FDFD”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Qu Luo, Limin Liu, Zhe Li, Qihao Peng +2 more
This paper proposes two new channel estimation methods for AFDM systems with FDFD shifts.
The paper proposes AdaBFL, a multi-layer defensive adaptive aggregation method that enhances Byzantine-robust federated learning by adaptively adjusting defense weights to counter complex poisoning at…
FedIDM introduces a novel federated learning framework that uses iterative distribution matching to achieve fast and stable convergence and maintain high model utility even when facing a large proport…
The paper proposes a new DDH-based technique that significantly reduces the key size of multi-party Distributed Point Function (DPF) secret sharing schemes, achieving an $O( oot{3}{N})$ key size for h…
The paper argues that the standard FID metric is unreliable because its performance depends significantly on the geometric structure and density of the reference dataset, not just the sample quality.
FedFG introduces a robust federated learning framework using flow-matching generation to simultaneously enhance client privacy and defend against sophisticated poisoning attacks.
Wei Sun, Yijun Chen, Bo Gao, Ke Xiong +3 more
The paper proposes PCDM, a diffusion-based framework that enables highly stealthy and effective data poisoning attacks against Federated Learning systems, significantly degrading global performance wh…
This paper proposes an MSDF accelerator for quantized U-Net segmentation that reduces computation dynamically and achieves high accuracy.
The paper introduces the Stanford EDGAR Filings Dataset (SEFD), an open-source corpus of financial documents for training and evaluating large language models.
This paper investigates the reproducibility of Frechet Inception Distance (FID) scores in image generation and proposes a new evaluation protocol.
Qu Luo, Lixia Xiao, Pei Xiao, Zilong Liu +5 more
This paper provides a systematic study of affine frequency division multiplexing (AFDM) from a standardization perspective.
Neha Vadnere, Yu-Ting Wang, Yitao Chen, Sreehari Sadesh +1 more
This paper proposes EdgeFaaS, a function-based edge computing framework that abstracts distributed and heterogeneous physical resources and provides consistent virtual interfaces for deploying and exe…
This paper introduces HIFI, a two-stage fine-tuning framework for statistical inference on parameters such as conditional means, which scales to large foundation models and reduces training compute.
Jun Xue, Zhuolin Yi, Yanzhen Ren, Yihuan Huang +5 more
This paper proposes a framework called Time-Frequency Consistency Learning (TFCL) to improve the robustness of speech deepfake detection (SDD) against distortions introduced by acoustic front-end (AFE…
FedTrident proposes a comprehensive framework to defend Federated Learning-based Road Condition Classification against Targeted Label-Flipping Attacks, achieving robust performance comparable to non-a…
This paper adapts a decision foundation model for disease classification from patient-reported symptoms, achieving high accuracy and low latency.