Machine Learning | Martin Renqiang Min

NEC Laboratories America, Inc. (NEC Labs) is the US-based center for NEC Corporation’s global network of corporate research laboratories. Our diverse research groups collaborate with industry, academia and governments to provide disruptive solutions to complex problems. A leader in the integration of IT and network technologies with more than 100 years of expertise, NEC provides a combination of products and solutions that cross-utilize the company’s experience and global resources to meet the complex and ever-changing needs of its customers.

Machine Learning | Martin Renqiang Min

Martin Renqiang Min

Publications

Conditional Image-to-Video Generation with Latent Flow Diffusion Models

Source-Free Video Domain Adaptation with Spatial-Temporal-Historical Consistency Learning

Exploring Compositional Visual Generation with Latent Classifier Guidance

T-Cell Receptor Optimization with Reinforcement Learning and Mutation Polices for Precision Immunotherapy

Binding Peptide Generation for MHC Class I Proteins with Deep Reinforcement Learning

On TCR Binding Predictors Failing to Generalize to Unseen Peptides

Attentive Variational Information Bottleneck for TCR–peptide interaction prediction

T-Cell Receptor-Peptide Interaction Prediction with Physical Model Augmented Pseudo-Labeling

StyleT2I: Towards Compositional and High-Fidelity Text-to-Image Synthesis

Learning Transferable Reward for Query Object Localization with Policy Adaptation

AE-StyleGAN: Improved Training of Style-Based Auto-Encoders

A Deep Generative Model for Molecule Optimization via One Fragment Modification

Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning

Towards Robustness of Deep Neural Networks via Networks via Regularization

Dual Projection Generative Adversarial Networks for Conditional Image Generation

DECODE: A Deep-learning Framework for Condensing Enhancers and Refining Boundaries with Large-scale Functional Assays

Hopper: Multi-hop Transformer for Spatio-Temporal Reasoning

Disentangled Recurrent Wasserstein Auto-Encoder

Ranking-based Convolutional Neural Network Models for Peptide-MHC Binding Prediction

Model-Based Autoencoders for Imputing Discrete single-cell RNA-seq Data

Improving Disentangled Text Representation Learning with Information Theoretical Guidance

S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation

Adversarial Cooperative Imitation Learning for Dynamic Treatment Regimes

Contact Us

About Us

Our Pages

Read Our Blog Posts