6 citations · 9 across the 9 of their papers we have counts for
14 papers
Opportunistic Conditional Entropy Coding with Frozen Analysis and Synthesis Transforms
Vincent Corlay, Maxime Rousselot, Andriy Enttsel
In many delivery settings, a receiver may already hold a lower-quality or lower-resolution representation of an image, obtained through an independent transmission. Conventional co…
How Many Posterior Samples? Calibrated Stopping for Adaptive Sensing
Vincent Corlay, Andriy Enttsel
In classification-oriented adaptive sensing, posterior samples characterize uncertainty at the current measurement state and can serve two roles: they may guide the next sensing di…
Classification-oriented adaptive sensing via posterior sampling
Andriy Enttsel, Maxime Rousselot, Vincent Corlay
Recent advances in diffusion models have enabled high-performance, instance-adaptive compressed sensing through posterior sampling, without task-specific policy training. Existing…
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…
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…
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…