DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images

Kavli Affiliate: Cheng Peng | First 5 Authors: Cheng Peng, S. Kevin Zhou, Rama Chellappa, , | Summary: Medical image super-resolution (SR) is an active research area that has many potential applications, including reducing scan time, bettering visual understanding, increasing robustness in downstream tasks, etc. However, applying deep-learning-based SR approaches for clinical applications often encounters […]


Continue.. DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images

Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

Kavli Affiliate: Cheng Peng | First 5 Authors: Yuxiang Guo, Cheng Peng, Chun Pong Lau, Rama Chellappa, | Summary: Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages […]


Continue.. Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

PARAGEN : A Parallel Generation Toolkit

Kavli Affiliate: Yi Zhou | First 5 Authors: Jiangtao Feng, Yi Zhou, Jun Zhang, Xian Qian, Liwei Wu | Summary: PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation. PARAGEN provides thirteen types of customizable plugins, helping users to experiment quickly with novel ideas across model architectures, optimization, and learning strategies. We […]


Continue.. PARAGEN : A Parallel Generation Toolkit

Diamond-like carbon coatings for cryogenic operation of particle detectors

Kavli Affiliate: Yi Zhou | First 5 Authors: Sara Leardini, Yi Zhou, Andrea Tesi, Miguel Morales, Diego González-Díaz | Summary: Characterization of diamond-like carbon (DLC) coatings at cryogenic temperatures (down to 77 K) is presented, covering the electrical resistivity range of practical interest to gaseous and liquid particle instrumentation: 10^-1-10^5 Mohm/sq. The good behaviour observed […]


Continue.. Diamond-like carbon coatings for cryogenic operation of particle detectors

Zero-Shot 3D Drug Design by Sketching and Generating

Kavli Affiliate: Yi Zhou | First 5 Authors: Siyu Long, Yi Zhou, Xinyu Dai, Hao Zhou, | Summary: Drug design is a crucial step in the drug discovery cycle. Recently, various deep learning-based methods design drugs by generating novel molecules from scratch, avoiding traversing large-scale drug libraries. However, they depend on scarce experimental data or […]


Continue.. Zero-Shot 3D Drug Design by Sketching and Generating

Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey

Kavli Affiliate: Biao Huang | First 5 Authors: R. Bhushan Gopaluni, Aditya Tulsyan, Benoit Chachuat, Biao Huang, Jong Min Lee | Summary: Over the last ten years, we have seen a significant increase in industrial data, tremendous improvement in computational power, and major theoretical advances in machine learning. This opens up an opportunity to use […]


Continue.. Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey

Lacing topological orders in two dimensions: exactly solvable models for Kitaev’s sixteen-fold way

Kavli Affiliate: Yi Zhou | First 5 Authors: Jin-Tao Jin, Jian-Jian Miao, Yi Zhou, , | Summary: A family of two-dimensional (2D) spin-1/2 models have been constructed to realize Kitaev’s sixteen-fold way of anyon theories. Defining a one-dimensional (1D) path through all the lattice sites, and performing the Jordan-Wigner transformation with the help of the […]


Continue.. Lacing topological orders in two dimensions: exactly solvable models for Kitaev’s sixteen-fold way

Finite-Time Error Bounds for Greedy-GQ

Kavli Affiliate: Yi Zhou | First 5 Authors: Yue Wang, Yi Zhou, Shaofeng Zou, , | Summary: Greedy-GQ with linear function approximation, originally proposed in cite{maei2010toward}, is a value-based off-policy algorithm for optimal control in reinforcement learning, and it has a non-linear two timescale structure with a non-convex objective function. This paper develops its finite-time […]


Continue.. Finite-Time Error Bounds for Greedy-GQ

Finite-Time Error Bounds for Greedy-GQ

Kavli Affiliate: Yi Zhou | First 5 Authors: Yue Wang, Yi Zhou, Shaofeng Zou, , | Summary: Greedy-GQ with linear function approximation, originally proposed in cite{maei2010toward}, is a value-based off-policy algorithm for optimal control in reinforcement learning, and it has a non-linear two timescale structure with the non-convex objective function. This paper develops its tightest […]


Continue.. Finite-Time Error Bounds for Greedy-GQ

Federated XGBoost on Sample-Wise Non-IID Data

Kavli Affiliate: Yi Zhou | First 5 Authors: Katelinh Jones, Yuya Jeremy Ong, Yi Zhou, Nathalie Baracaldo, | Summary: Federated Learning (FL) is a paradigm for jointly training machine learning algorithms in a decentralized manner which allows for parties to communicate with an aggregator to create and train a model, without exposing the underlying raw […]


Continue.. Federated XGBoost on Sample-Wise Non-IID Data