collaborators

6 papers

cs.LG2026

Fiaingen: A financial time series generative method matching real-world data quality

Jože M. Rožanec, Tina Žezlin, Laurentiu Vasiliu +3

Data is vital in enabling machine learning models to advance research and practical applications in finance, where accurate and robust models are essential for investment and tradi…

eess.IV2026

DQ-Ladder: A Deep Reinforcement Learning-based Bitrate Ladder for Adaptive Video Streaming

Reza Farahani, Zoha Azimi, Vignesh V Menon +4

Adaptive streaming of segmented video over HTTP typically relies on a predefined set of bitrate-resolution pairs, known as a bitrate ladder. However, fixed ladders often overlook v…

cs.LG2026

ELLMPEG: An Edge-based Agentic LLM Video Processing Tool

Zoha Azimi, Reza Farahani, Radu Prodan +1

Large language models (LLMs), the foundation of generative AI systems like ChatGPT, are transforming many fields and applications, including multimedia, enabling more advanced cont…

cs.LG2025

Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation

Mario Colosi, Reza Farahani, Maria Fazio +2

Data within a specific context gains deeper significance beyond its isolated interpretation. In distributed systems, interdependent data sources reveal hidden relationships and lat…

cs.DC2025

Serverless Everywhere: A Comparative Analysis of WebAssembly Workflows Across Browser, Edge, and Cloud

Mario Colosi, Reza Farahani, Lauri Loven +2

WebAssembly (Wasm) is a binary instruction format that enables portable, sandboxed, and near-native execution across heterogeneous platforms, making it well-suited for serverless w…

cs.DC2025

Toward Sustainability-Aware LLM Inference on Edge Clusters

Kolichala Rajashekar, Nafiseh Sharghivand, Radu Prodan +1

Large language models (LLMs) require substantial computational resources, leading to significant carbon emissions and operational costs. Although training is energy-intensive, the…