46 citations · 79 across the 9 of their papers we have counts for
11 papers
Using Language Models For Knowledge Acquisition in Natural Language Reasoning Problems
Fangzhen Lin, Ziyi Shou, Chengcai Chen
For a natural language problem that requires some non-trivial reasoning to solve, there are at least two ways to do it using a large language model (LLM). One is to ask it to solve…
Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts
Yuxin Pan, Fangzhen Lin
Traditional model-based reinforcement learning (RL) methods generate forward rollout traces using the learnt dynamics model to reduce interactions with the real environment. The re…
PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++
Jaewoo Song, Fangzhen Lin
Standard deep learning algorithms are implemented using floating-point real numbers. This presents an obstacle for implementing them on low-end devices which may not have dedicated…
Computing Class Hierarchies from Classifiers
Kai Kang, Fangzhen Lin
A class or taxonomic hierarchy is often manually constructed, and part of our knowledge about the world. In this paper, we propose a novel algorithm for automatically acquiring a c…
XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning
Yuxin Jiang, Ziyi Shou, Qijun Wang +2
This paper presents our submitted system to SemEval 2021 Task 4: Reading Comprehension of Abstract Meaning. Our system uses a large pre-trained language model as the encoder and an…
Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
Haodi Zhang, Zihang Gao, Yi Zhou +3
Deep reinforcement learning has been successfully used in many dynamic decision making domains, especially those with very large state spaces. However, it is also well-known that d…