3 papers
cs.LG2026
Expected Gain-based Escalation in Vertical Federated Learning
Mohamad Mestoukirdi, Vincent Corlay
Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to every sample can incur unnec…
eess.IV2026
Adaptive Transform Coding for Semantic Compression
Andriy Enttsel, Vincent Corlay
Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic em…
cs.IT2026
Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding
Andriy Enttsel, Vincent Corlay
Task-Oriented Source Coding (TOSC) has emerged as a paradigm for efficient visual data communication in machine-centric inference systems, where bitrate, latency, and task performa…