11 papers
When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability
Suraj Babu Thimma Krishnaram, Yibo Hu, Karthikeyan Saravanan
Hate moderation is often evaluated as classification on clean English inputs, but deployed systems must route content to actions such as ALLOW, FLAG, or REVIEW. We study how this w…
DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos +4
Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect…
DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
Haaris Mehmood, Jie Xu, Karthikeyan Saravanan +2
Federated learning (FL) enables the collaborative training of large-scale language models (LLMs) across edge devices while keeping user data on-device. However, FL still exposes se…
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
Jie Xu, Haaris Mehmood, Rogier Van Dalen +2
Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice,…
FlowW2N: Whispered-to-Normal Speech Conversion via Flow-Matching
Fabian Ritter-Gutierrez, Md Asif Jalal, Pablo Peso Parada +5
Whispered-to-normal (W2N) speech conversion aims to reconstruct missing phonation from whispered input while preserving content and speaker identity. This task is challenging due t…
Retrieval Augmented Generation based context discovery for ASR
Dimitrios Siskos, Stavros Papadopoulos, Pablo Peso Parada +3
This work investigates retrieval augmented generation as an efficient strategy for automatic context discovery in context-aware Automatic Speech Recognition (ASR) system, in order…