Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning
Melika Shirian, Kianoosh Vadaei, Kian Majlessi +4
We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-modal settings in a single, modul…
cs.LG2025
Delta-Audit: Explaining What Changes When Models Change
Arshia Hemmat, Afsaneh Fatemi
Model updates (new hyperparameters, kernels, depths, solvers, or data) change performance, but the \emph{reason} often remains opaque. We introduce \textbf{Delta-Attribution} (\mbo…
cs.LG2024
Context Awareness Gate For Retrieval Augmented Generation
Mohammad Hassan Heydari, Arshia Hemmat, Erfan Naman +1
Retrieval Augmented Generation (RAG) has emerged as a widely adopted approach to mitigate the limitations of large language models (LLMs) in answering domain-specific questions. Pr…