Linear video coding
Conventional and learning-based video compression — codecs, rate–distortion, and the boundary between hand-designed and neural pipelines.
Active research group · LTCI
Multimedia team - at LTCI, Télécom Paris, Institut Polytechnique de Paris
The Multimedia (MM) team conducts research on the full life-cycle of multimedia data: from compression and transport to learning, explainability, and generation. We work where signal processing meets modern deep learning — with an emphasis on frugal, geometric, and multimodal approaches.
132+
Publications
2021–2026, peer-reviewed
30
Team members
faculty, postdocs & students
7
Research themes
from coding to learning
A*
Top venues
WACV · ICCV · NeurIPS · ICLR
WACVICCVNeurIPSICLRCVPRICIPECCVNeurocomputingAAAIICCVWICMLICPRIJCNNSSP
WACVICCVNeurIPSICLRCVPRICIPECCVNeurocomputingAAAIICCVWICMLICPRIJCNNSSP
What we work on
All themes →Rich-media scene representation
Representing complex scenes with multiple media, layouts, and interactions — beyond a single video stream.
Multimedia content adaptation
Adapting multimedia content to networks, devices, and users — quality of experience under constraints.
Multimedia distribution networks
Transport, orchestration, and protocols for delivering multimedia at scale.
Frugal and efficient AI
Pruning, quantization, low-rank methods, and other tools to make deep models small enough to deploy.
Geometric deep learning
Learning on graphs, manifolds, and structured domains — where the geometry of the data shapes the architecture.
Latest news
All news →- NeurIPS 2026
Four papers accepted at NeurIPS 2026
We are happy to announce that four papers from the Multimedia team have been accepted at NeurIPS 2026.
New hired professor
We are happy to welcome Xiaoran Jiang as a new Maître de Conférences in our équipe!
New ANR JCJC project
Many congratulations to Stephan Alaniz who has received funding for his ANR JCJC project (VieLM).
Recent work
All publications →A Sparse Low-Rank Biclique Decomposition for Graphs
Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models
SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
Uncertainty as an Underconstrained Axis in Lossy Compression
AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models