Skip to main content
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.

ICML · 10 Jul 2026
ICML · 10 Jul 2026
journéeIDS · 2 Jul 2026
journéeIDS · 2 Jul 2026
CVPR · 6 Jun 2026
CVPR · 6 Jun 2026
ICCV · 3 Oct 2025
ICCV · 3 Oct 2025

We're recruiting

PhD students, postdocs, research engineers, and interns working on frugal AI, multimedia coding, and multimodal learning.

Due to the very large volume of solicitations we receive, spontaneous applications sent by email will be ignored. Please apply through the application form.

How to apply →
137+
Publications
2021–2026, peer-reviewed
32
Team members
faculty, postdocs & students
7
Research themes
from coding to learning
A*
Top venues
WACV · NeurIPS · ICCV · ICLR
WACVNeurIPSICCVICLRCVPRICIPECCVNeurocomputingAAAIICCVWICMLICPRIJCNNSSP WACVNeurIPSICCVICLRCVPRICIPECCVNeurocomputingAAAIICCVWICMLICPRIJCNNSSP

What we work on

All themes →

Linear video coding

Conventional and learning-based video compression — codecs, rate–distortion, and the boundary between hand-designed and neural pipelines.

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 →
Conference on Neural … · 2026

A Sparse Low-Rank Biclique Decomposition for Graphs

Antoine Vialle, Sergei Gerasimov, Aref Einizade, Antonio Ortega, Fragkiskos D. Malliaros, Jhony H. Giraldo

Conference on Neural … · 2026

Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models

Imad Eddine Marouf, Khalid Oublal, Enzo Tartaglione, Stéphane Lathuilière

Conference on Neural … · 2026

Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation

Mariam Hassan, Kaouther Messaoud, Wuyang Li, Alexandre Alahi

Conference on Neural … · 2026

SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers

Enzo Tartaglione, Vito Paolo Pastore

Conference on Neural … · 2026

Uncertainty as an Underconstrained Axis in Lossy Compression

Enzo Tartaglione

European Conference on … · 2026

AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors

Vito Paolo Pastore, Massimiliano Ciranni, Enzo Tartaglione, Vittorio Murino