Steven Chu Hong Hoi

5 papers · 2020–2022 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

NeurIPS (5)

Top co-authors

Caiming Xiong (4) Pan Zhou (3) Jiashi Feng (1) Akhilesh Deepak Gotmare (1) Chao Ma (1) Silvio Savarese (1) Junnan Li (1) Ramprasaath Selvaraju (1) Hung Le (1) Yue Wang (1)

Research topics

Machine Learning (4) Deep Learning (2) Core Methods (2) Learning Types · Machine Learning (2) Optimization & Theory (2) Artificial Intelligence (1) Reinforcement Learning (1) Applications (1) Core AI (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Models (1) Techniques (1)

Keywords

representation learning (2) image classification (2) contrastive learning (2) self-supervised learning (1) code generation (1) program synthesis (1) network optimization (1) semantic similarity (1) adam optimizer (1) stochastic differential equation (1) zero-shot transfer (1) generalization gap (1) image-text retrieval (1) pre-trained language model (1) skip connection (1) flat minima (1) functional correctness (1) vision language (1) multimodal encoder (1) heavy-tailed gradient noise (1)

Papers

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning NeurIPS 2022 Align before Fuse: Vision and Language Representation Learning with Momentum Distillation NeurIPS 2021 A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning NeurIPS 2021 Theory-Inspired Path-Regularized Differential Network Architecture Search NeurIPS 2020 Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning NeurIPS 2020