36 citations · 77 across the 7 of their papers we have counts for
7 papers
The Triangle of Similarity: A Multi-Faceted Framework for Comparing Neural Network Representations
Olha Sirikova, Alvin Chan
Comparing neural network representations is essential for understanding and validating models in scientific applications. Existing methods, however, often provide a limited view. W…
How to Make Large Language Models Generate 100% Valid Molecules?
Wen Tao, Jing Tang, Alvin Chan +5
Molecule generation is key to drug discovery and materials science, enabling the design of novel compounds with specific properties. Large language models (LLMs) can learn to perfo…
FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding
Bill Tuck Weng Pung, Alvin Chan
Inducing latent tree structures from sequential data is an emerging trend in the NLP research landscape today, largely popularized by recent methods such as Gumbel LSTM and Ordered…
RNA Alternative Splicing Prediction with Discrete Compositional Energy Network
Alvin Chan, Anna Korsakova, Yew-Soon Ong +3
A single gene can encode for different protein versions through a process called alternative splicing. Since proteins play major roles in cellular functions, aberrant splicing prof…
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with Parameters
Aston Zhang, Yi Tay, Shuai Zhang +4
Recent works have demonstrated reasonable success of representation learning in hypercomplex space. Specifically, "fully-connected layers with Quaternions" (4D hypercomplex numbers…
Player Identification in Hockey Broadcast Videos
Alvin Chan, Martin D. Levine, Mehrsan Javan
We present a deep recurrent convolutional neural network (CNN) approach to solve the problem of hockey player identification in NHL broadcast videos. Player identification is a dif…
CoCon: A Self-Supervised Approach for Controlled Text Generation
Alvin Chan, Yew-Soon Ong, Bill Pung +2
Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LM…