Shawn Tan

9 papers · 2018–2025 · 5 venues · 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 ↓

🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🔥 Unstoppable · Bronze

Venues

ICLR (3) EMNLP (2) NeurIPS (2) ACL (1) NAACL (1)

Top co-authors

Yikang Shen (7) Aaron Courville (7) Alessandro Sordoni (6) Chin-Wei Huang (2) Aaron C. Courville (2) Peng Li (1) Chuang Gan (1) Rameswar Panda (1) Zhenfang Chen (1) Timothy J. O’Donnell (1)

Research topics

Deep Learning (8) Architectures (6) Machine Learning (5) Artificial Intelligence (3) Natural Language Processing (3) Core AI (3) Generation (2) Learning Types (2) Models (2) Optimization & Theory (2) Techniques (2) Understanding (2) Interdisciplinary (1) Application Areas (1) Core Methods (1)

Keywords

language model (2) ordered memory (2) variational inference (2) tree structure (2) attention mechanism (1) dependency parsing (1) self-attention mechanism (1) compositional generalization (1) natural language processing (1) parameter sharing (1) incremental parsing (1) stick-breaking process (1) generative model (1) computational efficiency (1) long short-term memory (1) recursive neural network (1) recurrent neural network (1) inductive bia (1) normalizing flow (1) model architecture (1)

Papers

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study ICLR 2025 Sparse Universal Transformer EMNLP 2023 Learning to Dequantise with Truncated Flows ICLR 2022 Unsupervised Dependency Graph Network ACL 2022 Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle NAACL 2021 Recursive Top-Down Production for Sentence Generation with Latent Trees EMNLP 2020 Ordered Memory NeurIPS 2019 Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks ICLR 2019 Improving Explorability in Variational Inference with Annealed Variational Objectives NeurIPS 2018