Image Editing Of Complex Visual Scene Via Natural Language H/F
il y a 2 jours
OverviewImage Editing of Complex Visual Scene via Natural Language H/FOrganizationThe French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas: defence and security; nuclear energy (fission and fusion); technological research for industry; fundamental research in the physical sciences and life sciences. The LIST is part of CEA Tech and focuses on intelligent digital systems. Within LIST, the Laboratory of Vision and Learning for Scene Analysis (LVA) conducts research in computer vision and AI for perception of intelligent and autonomous systems. Based in Saclay (Essonne).ReferenceReference 2025-37545ContractInternshipJob locationSaclaySubjectThis internship focuses on natural language-guided image editing, aiming at generating and modifying complex scenes from verbal descriptions. The candidate will design and implement methods to interpret language for creating or editing detailed images (e.g., crowds, cityscapes, multi-object interactions). Key challenges include managing scene complexity—ensuring coherence and accuracy when multiple objects and relations are involved—and achieving effective multimodal integration between NLP and vision models.ResponsibilitiesDesign and implement methods to interpret language for creating or editing detailed images from verbal descriptions.Handle scene complexity to maintain coherence and accuracy when multiple objects and relations are present.Explore multimodal integration between natural language processing and computer vision models.Investigate current methods for natural language-based image generation and editing; develop innovative approaches; demonstrate improvements in accuracy and detail; contribute to academic research through publications and/or patents.Methods / MeansComputer Vision / ML (deep learning, GenAI…); Python (PyTorch, TensorFlow)QualificationsStudents in their 5th year of studies (M2)Computer vision skillsMachine learning skills (deep learning, LLM, VLM, generative AI)Python proficiency in a deep learning framework (especially PyTorch or TensorFlow)SiteSaclay #J-18808-Ljbffr
-
Image Editing of Complex Visual Scene via Natural Language H/F
il y a 9 heures
Saclay, Île-de-France CEA Temps pleinGeneral information Organisation The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas :• defence and security,• nuclear energy (fission and fusion),• technological research for industry,• fundamental research in the physical sciences and life sciences.Drawing...
-
Saclay, France CEA Temps pleinAccurate 3D scene reconstruction from images with neural Method H/F Référence 2025-37890 Based in Saclay (Essonne), the LIST is one of the two institutes of CEA Tech, the Technological Research Division of the CEA. Dedicated to intelligent digital systems, its mission is to carry out technological developments of excellence on behalf of industrial...
-
Saclay, France CEA Temps pleinFormal methodology for the exploration and the evaluation of complex critical SW architecture M/F Category: Mathematics, information, scientific, software Contract: Internship (6 months) Position description: The internship aims to implement and improve the formalization and implementation of an iterative methodology for critical embedded software...
-
Saclay, Île-de-France CEA Temps pleinPosition descriptionCategoryMathematics, information, scientific, softwareContractInternshipJob titleFormal methodology for the exploration and the evaluation of complex critical SW architecture M/FSubjectThe internship aims to implement and improve the formalization and implementation of an iterative methodology for critical embedded software architectures...
-
Saclay, France CEA Temps pleinRuntime Root-Cause Analysis for Intelligent Robots via Causal AI Techniques H/F Contract: Internship (6 months) Location: Saclay, France (Palaiseau, Essonne) Industry: Research Services Employment Type: Internship – Seniority level: Not applicable Position Description Root‑Cause Analysis (RCA) identifies the fundamental cause of failures, not just...
-
Saclay, Île-de-France CEA Temps pleinInformations générales Entité de rattachement Le CEA est un acteur majeur de la recherche, au service des citoyens, de l'économie et de l'Etat.Il apporte des solutions concrètes à leurs besoins dans quatre domaines principaux : transition énergétique, transition numérique, technologies pour la médecine du futur, défense et sécurité sur un...
-
Saclay, Île-de-France CEA Temps pleinMissions:During this internship, you will explore integration of 3D reconstruction and natural language commands via large language models for a smart mobile robot (robot base + manipulator arm). The internship may notably include (depending on task advancement):Reviewing existing literature on the subjectDownloading and testing the best approaches...
-
Saclay, Île-de-France CEA Temps pleinRejoignez-nous en Stage CEA Tech Corporate from CEA Tech on Vimeo .En tant que stagiaire au CEA, vous aurez l'opportunité de travailler au sein d'un environnement de recherche de renommée mondiale. Nos équipes sont composées d'experts passionnés et dédiés, offrant un cadre propice à l'apprentissage et à la collaboration. Vous aurez accès à des...
-
Saclay, Île-de-France CEA Temps pleinInformations générales Entité de rattachement Le CEA est un acteur majeur de la recherche, au service des citoyens, de l'économie et de l'Etat.Il apporte des solutions concrètes à leurs besoins dans quatre domaines principaux : transition énergétique, transition numérique, technologies pour la médecine du futur, défense et sécurité sur un...
-
Saclay, France CEA Temps pleinStage – Téléopération robotique via motion‑capture et casque XR Mathématiques, information scientifique, logiciel Description du poste Votre mission principale sera d’intégrer un casque de réalité étendue (Meta Quest 3) à notre jumeau numérique, en développant les fonctionnalités de téléopération robotique et de visualisation les plus...
