headerSearch form

search string

Samsung Advanced Institute of Technology

main page

Global Labs

SAIT collaborates with talented people around the world to keep abreast of state-of-the-art technologies, drive new trends, and
create opportunities. Through Open Innovation, SAIT's global labs located in Yokohama, Beijing, San Jose, Boston, Moscow, Bengaluru, London, Frankfurt collaborate with regional universities, labs, and companies to create better technologies for all.

SAIT
Global R&D

Overview

SAIL Montreal (SAIT AI Lab Montreal) is a recently established academic-style research lab (in close collaboration with Mila) whose mission is to push the boundaries of AI with SAIT and Mila through open fundamental research. Headed by Simon Lacoste-Julien, professor in computer science at Université de Montréal and co-founding member of Mila, SAIL is located in Mila's corporate space at the heart of the Montreal AI ecosystem nearby Element AI, Borealis AI, FAIR, Microsoft Research and others where an open collaborative environment is encouraged.

Research Areas & Core Activities

Current research themes for the lab are: optimization and generalization in machine learning, with applications to structured data such as in natural language understanding or computer vision; interpretability of deep models, causal modeling and explainable AI; neural network compression and graph neural networks. Interaction with visitors from the AI and Software research center from SAIT (Samsung Advanced Institute of Technology) in Korea is encouraged. Their research interests include deep learning, natural language processing, visual recognition, neural processor and autonomous driving, among others.

People

Simon Lacoste-Julien

VP Lab director

Website Scholar

Damien Scieur

Research Scientist

Website Scholar

Reza Babanezhad

Research Scientist

Website Scholar

Yash Goyal

Research Scientist

Website Scholar

Marwa El Halabi

Research Scientist

Website Scholar

Yan Zhang

Research Scientist

Website Scholar

Aristide Baratin

Research Scientist

Website Scholar

Boris Knyazev

Research Scientist

Website Scholar

Alexia Jolicoeur-Martineau

Research Scientist

Website Scholar

Sebastien Lachapelle

Research Scientist

Website Scholar

Geneviève Bernard

Office Manager

Kiho Cho

Visiting Research Scientist 2023-24

Scholar

Eunhee Kang

Visiting Research Scientist 2022-23

Scholar

Ji-Hye Kim

Visiting Research Scientist 2022

Scholar

Doha Hwang

Visiting Research Scientist 2021-22

Scholar

Hwidong Na

Visiting Research Scientist in 2020

Website

NamYeong Kwon

Visiting Research Scientist in 2020

Scholar

Code

Github Huggingface

Publications

Promoting Exploration in Memory-Augmented Adam using Critical Momenta

Authors Pranshu Malviya, Goncalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang,

Simon Lacoste-Julien, Razvan Pascanu, Sarath Chanda

Conference TMLR

Improved Generalization of Weight Space Networks via Augmentations

Authors Aviv Shamsian, Aviv Navon, David W. Zhang, Yan Zhang, Ethan Fetaya, Gal Chechik, Haggai Maron

Conference ICML 2024

Unsupervised Concept Discovery Mitigates Spurious Correlations

Authors Md Rifat Arefin, Yan Zhang, Aristide Baratin, Francesco Locatello, Irina Rish, Dianbo Liu, Kenji Kawaguchi

Conference ICML 2024

A Sparsity Principle for Partially Observable Causal Representation

Authors Danru Xu, Dingling Yao, Sebastien Lachapelle, Perouz Taslakian, Julius von K？gelgen, Francesco Locatello,

Sara Magliacane

Conference ICML 2024

Lookbehind-Sam: k steps back, 1 step forward

Authors Goncalo Mordido, Pranshu Malviya, Aristide Baratin, Sarath Chandar

Conference ICML 2024

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging

Authors Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song

Conference ICML 2024

PopulAtion Parameter Averaging (PAPA)

Authors Alexia Jolicoeur-Martineau, Emy Gervais, Kilian FATRAS, Yan Zhang, Simon Lacoste-Julien

Conference Transactions of Machine Learning Research (TMLR)

MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Learning

Authors Oscar Manas, Pau Rodriguez*, Saba Ahmadi*, Aida Nematzadeh, Yash Goyal,

Aishwarya Agrawal* denotes equal contribution

Conference EACL 2023

Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees

Authors Alexia Jolicoeur-Martineau, Kilian Fatras, Tal Kachman

Conference AISTATS 2024

Fairness in Submodular Maximization over a Matroid Constraint

Authors Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong

Conference AISTATS 2024

Adaptive Quasi-Newton and Anderson Acceleration Framework with Explicit Global (Accelerated) Convergence Rates

Authors Damien Scieur

Conference AISTATS 2024

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Authors Miltiadis Kofinas, David W. Zhang, Boris Knyazev, Yan Zhang, Yunlu Chen, Gertjan J. Burghouts, Efstratios Gavves,

Cees G. M. Snoek

Conference ICLR 2024

How connectivity structure shapes rich and lazy learning in neural circuits

Authors Yuhan Helena Liu, Aristide Baratin, Jonathan Cornford, Stefan Mihalas, Eric Todd SheaBrown, Guillaume Lajoie

Conference ICLR 2024

Object centric architectures enable efficient causal representation learning

Authors Amin Mansouri, Jason Hartford, Yan Zhang, Yoshua Bengio

Conference ICLR 2024

Multi-View Causal Representation Learning with Partial Observability

Authors Dingling Yao, Danru Xu, Sebastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius,

Julius von Kügelgen, Francesco Locatello

Conference ICLR 2024

Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods

Authors Yuchen Liu, Zhen Liu, Aristide Baratin, Romain Laroche, Aaron Courville, Alessandro Sordoni

Conference TMLR (Nov-23)

Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees

Authors Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad Harikandeh, Nicolas Le Roux

Conference NeurIPS 2023

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Authors Sébastien Lachapelle, Divyat Mahajan, Ioannis Mitliagkas, Simon Lacoste-Julien

Conference NeurIPS 2023

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

Authors Boris Knyazev, Doha Hwang, Simon Lacoste-Julien

Conference ICML 2023

Difference of submodular minimization via DC programming

Authors Marwa El Halabi, George Orfanides, Tim Hoheisel

Conference ICML 2023

Fairness in Streaming Submodular Maximization over a Matroid Constraint

Authors Marwa El Halabi*, Ashkan Norouzi-Fard*, Jakab Tardos*, Jakub Tarnawski*, Federico Fusco*

Conference ICML 2023

Unlocking Slot Attention by Changing Optimal Transport Costs

Authors Yan Zhang*, David W Zhang*, Simon Lacoste-Julien, Gertjan J Burghouts, Cees GM Snoek

Conference ICML 2023

Equivariance with Learned Canonicalization Functions

Authors Sékou-Oumar Kaba*, Arnab Kumar Mondal*, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh

Conference ICML 2023

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

Authors Jihye Kim, Aristide Baratin, Yan Zhang, Simon Lacoste-Julien

Conference ICML 2023

Fast Online Node Labelling with Local and Global Consistency

Authors Baojian Zhou, Yifan Sun, Reza Babanezhad

Conference ICML 2023

Target-based Surrogates for Stochastic Optimization

Authors J. Wilder Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux

Conference ICML 2023

Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty

Authors Thomas George, Guillaume Lajoie, Aristide Baratin

Journal TMLR (Dec-22)

Nonlinear acceleration of momentum and primal-dual algorithms

Authors Raghu Bollapragada, Damien Scieur, Alexandre d’Aspremont

Journal Mathematical Programming (Feb-22)

Acceleration in Optimization

Authors Alexandre d'Apresmont, Adrien Taylor, Damien Scieur

Journal Foundation and Trends© in Optimization (Dec-21)

SVRG meets AdaGrad: Painless Variance Reduction

Authors Benjamin Dubois-Taine, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Simon Lacoste-Julien

Journal Machine Learning Journal (Nov-22)

The Curse of Unrolling: Rate of Differentiating Through Optimization

Authors Damien Scieur, Quentin Bertrand, Gauthier Gidel and Fabian Pedregosa

Conference Neurips 2022

Data-Efficient Structured Pruning via Submodular Optimization

Authors Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien

Conference Neurips 2022

Hyper-Representations as Generative Models: Sampling Unseen Neural NetworkWeights

Authors Konstantin Schürholt, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth

Conference Neurips 2022

MCVD: Masked Conditional Video Diffusion for Prediction

Authors Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal

Conference Neurips 2022

Model Zoos: A Dataset of Diverse Populations of Neural Network Models

Authors Konstantin Schürholt, Diyar Taskiran, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth

Conference Neurips 2022

Towards Painless Policy Optimization for Constrained MDPs

Authors Arushi Jain, Sharan Vaswani, Reza Babanezhad Harikandeh, Csaba Szepesvari, Doina Precup

Conference UAI 2022

Only tails matter: Average-Case Universality and Robustness in the Convex Regime

Authors Leonardo Cunha, Gauthier Gidel, Fabian Pedregosa, Courtney Paquette, Damien Scieur

Conference ICML 2022

Towards Noise-adaptive, Problem-adaptive (Accelerated) SGD

Authors Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad

Conference ICML 2022

Image Retrieval from Contextual Descriptions

Authors Benno Krojer, Vaibhav Adlakha, Vibhav Vineet, Yash Goyal, Edoardo Ponti, Siva Reddy

Conference ACL 2022

Super-Acceleration with Cyclical Step-sizes

Authors Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien Taylor, Fabian Pedregosa

Conference AISTATS 2022

MULTISET-EQUIVARIANT SET PREDICTION WITH APPROXIMATE IMPLICIT DIFFERENTIATION

Authors Yan Zhang, David W Zhang, Simon Lacoste-Julien, Gertjan J. Burghouts, Cees G. M. Snoek

Conference ICLR 2022

On Evaluation Metrics for Graph Generative Models

Authors Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor

Conference ICLR 2022

Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport

Authors Lewis Liu, Yufeng Zhang, Zhuoran Yang, Reza Babanezhad, Zhaoran Wang

Conference ICML 2021 (Jul-21)

Connecting Sphere Manifolds Hierarchically for Regularization

Authors Damien Scieur, Youngsung kim

Conference ICML 2021 (Jul-21)

Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets

Authors Thomas Kerdreux, Lewis Liu, Simon Lacoste-Julien, Damien Scieur

Conference ICML 2021 (Jul-21)

Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning

Authors Namyeong Kwon, Hwidong Na, Gabriel Huang, Simon Lacoste-Julien

Conference ICLR 2021 (Sep-21)

Average-case Acceleration for Bilinear Games and Normal Matrices

Authors Carles Domingo-Enrich, Fabian Pedregosa, Damien Scieur

Conference ICLR 2021 (Sep-21)

An Analysis of the Adaptation Speed of Causal Models

Authors Remi Le Priol, Reza Babanezhad, Yoshua Bengio, Simon Lacoste-Julien

Conference AISTATS 2021 (Apr-21)

Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant Updates

Authors Damien Scieur, Lewis Liu, Thomas Pumir, Nicolas Boumal

Conference AISTATS 2021 (Apr-21)

Extra-gradient with player sampling for provable fast convergence in n-player games

Authors Samy Jelassi, Carles Domingo Enrich, Damien Scieur, Arthur Mensch, Joan Bruna

Conference ICML 2020 (Jul-20)

Universal Average-Case Optimality of Polyak Momentum

Authors Damien Scieur, Fabian Pedregosa

Conference ICML 2020 (Jul-20)

Average-case Acceleration Through Spectral Density Estimation

Authors Fabian Pedregosa, Damien Scieur

Conference ICML 2020 (Jul-20)

Accelerating Smooth Games by Manipulating Spectral Shapes

Authors Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel

Conference AISTATS 2020 (Aug-20)

Address & Contact

Montreal
6666 St Urbain St, Suite 200, Montreal, QC H2S 3H1,
e-mail address : g.bernard@samsung.com

Overview

Samsung R&D Institute Japan(SRJ) was established in August 1992, leading its research and development activities in Japan. In April 2002, SRJ opened another research facility located in Osaka, the second largest city in Japan. Over the past 20 years, SRJ has contributed to many of Samsung's core businesses; innovative research and developments in the field of Home Appliance, Mechatronics Technology, Image Processing, Display Materials, Ceramics, Secondary Battery, and so on.

Research Areas & Core Activities

Research activity is focusing in the following areas; electronic materials and devices for next generation display, secondary battery, and advanced technologies for consumer electronics and semiconductor and sensor device.

We believe that innovation comes from the creativity and insight stimulated with the interaction of academia. Partnerships with leading universities and institutes are indispensable for SRJ's research and development activities. SRJ is actively conducting more than 100 research partnerships every year with universities and research institutes in Japan.

SRJ is moving to invest considerable resources in fundamental R&D topics with strong innovations in Japan. Our competence in materials and devices and advanced consumer electronics technologies is a key success factor in Samsung's new business and technical breakthrough.

Address & Contact

Yokohama
2-7 Sugasawa-cho, Tsurumu-ku, Yokohama, Japan
+81-45-510-3336
Osaka
Minoh Semba Center Bldg., 2-1-11 Semba Nishi, Mino, Osaka, Japan
+81-72-730-2173

Overview

SAIT established SAIT-America offices in Silicon Valley, Boston, and Pasadena to lead ground-breaking research. SAIT-America is strategically located near cutting edge R&D activities of prestigious academic institutions, renowned companies, and exciting startups. Officially opened in May 2011, SAIT-America’s mission is to plant the seeds of innovative technologies that will bloom and yield next generation Samsung products in 5 to 10 years. We aim to achieve this by collaborating with the most innovative minds in the world.

Research Areas & Core Activities

The Silicon Valley lab is developing new architectures of neural network processors for AI applications. Current AI needs big data centers or cloud servers with many GPU chips. Our aim is to bring down the massive size of algorithms, and at the same time to radically increase the processing power of neural network processors, thereby enabling AI capability on mobile phones or autonomous cars, which will have big impact to people’s lives and the society.

The Boston lab mainly focuses its effort on Materials research and development, with a special emphasis on next-generation energy storage and battery. Our engineers use computational simulations to explore and develop next-generation energy solutions.

The Pasadena lab focuses on next generation image sensor technologies for LIDAR and 3D depth sensors.

In addition to R&D, SAIT-America is the liaison between SAIT-HQ and the most innovative minds in North America for our open innovation efforts. We strive to create strong research relationships with top U.S. institutions and universities by embarking on innovative collaborations. We look forward to partnering with you.

Address & Contact

Silicon Valley
665 Clyde Ave. Mountain View, CA 94043
+1-650-584-2141
Boston
3 Van De Graaff Dr. STE 4 Brurlington MA 01803
+1-650-336-3508
Pasadena
2N Lake Ave, Ste 230, Pasadena, CA 91101
+1-626-683-3465

Overview

Since 1995, SAIT has enjoyed a long-standing research collaboration with various Russian academic and R&D organizations. The scientific partnership has focused on pioneering industry research domains including the development of optics such as next generation Display and m-Healthcare.

In February 2012, With expanding on its technology intelligence and outsourcing activities in Russia, SAIT officially inaugurated SAIT-Russia as one of the key overseas research sites to build upon frontier research based on fundamental Russian science.

SAIT-Russia is located in northern area of Moscow and provides talented Russian scientists and engineers with enhanced opportunities to collaborate with Samsung and SAIT.

Research Areas & Core Activities

Based on its long experience with the Russian Academy of Sciences as well as several prestigious universities in the fields of physics, chemistry and mathematics, SAIT-Russia initiated many advanced research projects across multiple disciplines including nano optics and plasmonics, digital holography and glass-free 3D display, m-healthcare and clinical test, computational predication of new materials, and so on.

SAIT-Russia aims to be one of the most prestigious research laboratories in Russia, where many of Russia's most talented scientists and engineers seek to follow their dreams, helping to lead innovation at SAIT and the world.

Address & Contact

Moscow
Office 1401, 12, Dvintsev Street, Building 1, Moscow, 127018, Russia
+7-495-797-2448

Overview

SAIT-China was founded in June 2008 with the mandate to "Set up a R&D base for future core-technology & China's leading technologies". The organization comprises three research groups, and a strategic planning group.

SAIT-China is located in Chaoyang District, Beijing - the R&D center of China with top Universities, prestigious research institutions, renowned companies and fast-evolving startups, which provides talented researchers and collaboration opportunities for Samsung and SAIT.

Research Areas & Core Activities

The research focuses of the SAIT-China Lab are AI for vision, including human understanding, interaction intelligence and visual computing. We have contributed core technologies for Samsung's flagship product including face/ landmark/ liveness detection for face unlock solution. We also obtained top rank 1 results on public benchmark dataset including FDDB (2017) and PASCAL 3D+ (2018).

SAIT-China aims to achieve scientific eminence through exploratory research to advance Samsung's existing offerings and become one of the most influential research labs in China. We are collaborating with China top Universities and research institutes, working on world-leading innovative algorithms and technologies.

SAIT-China is actively expanding its local R&D network to enhance the development of innovative core technologies based on China's particular scientific and technical strengths.

Address & Contact

Beijing
100028 (17F A-29), Sun Palace Building, No.12-A, Taiyanggong Mid Road, Chaoyang District, Beijing
+86-10-8443-9777
Xian
B-1 Building, Xian Software Town Phase 2, No. 156 Tiangu 8th Rd, Hi-tech Zone, XiAn, Shaanxi, China

Overview & Core Activities

SAIT-Europe was established in Samsung Research U.K. in 2007. SAIT-Europe actively senses for future technologies in Europe; targeting world class industry, universities, research institutes, ventures and spin outs for collaborative frontier R&D and technology transfer projects

As part of our 'open innovation' activities we engage experts internationally to build collaborative research relationships via a range of avenues including:

- Research Partner programs
- Researcher Secondment, Researcher Advisory Boards
- 1:1 Bilateral R&D Project Funding
- Country & EU Consortia R&D
- Joint Venture and Spinout Support, IP and Tech Transfer.
- Annual Global Research Outreach (GRO) program

Our mission is to provide a bridge between Samsung and the best R&D in Europe to ensure a bright future of Samsung. Our vision is to be a "centre of excellence in open innovation", capturing innovative ideas and maximizing competence in Europe.

Address

London
Samsung R&D Institute UK, Communications House, South Street, Staines-upon- Thames, Surrey, TW18 4QE, UK., Staines-Upon-Thames, United Kingdom
+44-1784-428-600

Overview

Samsung set-up dedicated development center called Samsung India Software Operations (SISO) in 1996 primarily leveraging the India's growing IT prowess. Since then SISO has grown to become the largest overseas R&D center of Samsung outside Korea. Today, 4000+ strong workforces are providing wide variety of software solutions to various business units of Samsung.

The dedicated R&D group called SAIT-India was established in 2009 with an aim to conduct research and development primarily in Future IT areas. This group is actively involved in the research on advanced topics in IT by working closely with the research groups in SAIT, Korea. SAIT-India has since also expanded its scope to include research topics in the non-IT areas thus contributing to the India ecosystem by leveraging the best local talent. This group currently comprises of 80 engineers with many researcher with advanced degree or work experience from abroad.

Research Areas & Core Activities

Research conducted in SAIT-India encompass various disciplines including Computer science, Advanced Communications, Intelligent computing, Bioinformatics, Computational Materials Science. etc.

We are on course to become one of the leading R&D establishments in India measured by patents and publications. SAIT-India continues to attract top talent in the country and today comprises of 70+ members with advanced degrees from leading institutions in India and abroad.

SAIT-India in particular and SISO in general continue to build relationship with top Indian institutions co-working on advanced research topics. Our clear vision to build on the India's IT competency to drive innovation in multiple disciplines, thus contributing to Samsung's vision of creating new technologies reaching every individual on the globe.

Address & Contact

Bangalore
Phoenix B'd, Bagmane Constellation business Park Bangalore Karnataka, India 06765
+91-80-4181-9999

Overview

Samsung R&D Institute Ukraine was established in Kiev in 2009.
Our key technologies of us, which are strengthening its technological development to enhance the competitiveness of Samsung products, are Security, AI and AR/VR areas.

Research Areas & Core Activities

We are composed of prominent professionals and are working on the study of intelligence security, computer vision, context-aware intelligent service etc.

As a way to enhance collaboration between Samsung and local education system, cooperation with Top Tier Universities for Research projects in AI and Security domains and internship program was established, where Intern can participate in real project and have opportunity to get a job for the best graduates in mid-term.

We also support Corporate Social Responsibility. On this basis, coding courses were developed, which are run by our engineers for students and professors. Following the results of the Samsung Developer’s Academy project, Smart Class was installed in Kyiv Polytechnic Institute.

Address & Contact

Kiev
57 L'va Tolstogo Street, Kiev Ukraine 01032
+380-44-392-1736

Samsung Advanced Institute of Technology

Global Labs

SAIT Global R&D

Overview

Research Areas & Core Activities

People

Code

Publications

Related Contents

Address & Contact

Overview

Research Areas & Core Activities

Address & Contact

Overview

Research Areas & Core Activities

Address & Contact

Overview

Research Areas & Core Activities

Address & Contact

Overview

Research Areas & Core Activities

Address & Contact

Overview & Core Activities

Address

Overview

Research Areas & Core Activities

Address & Contact

Overview

Research Areas & Core Activities

Address & Contact

SAIT
Global R&D