Hang Xu

EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

2021 · arXiv (Cornell University)

Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge devices. In this paper, we have …

OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research

2023 · IEEE Transactions on Neural Networks and Learning Systems

Owing to the unremitting efforts from a few institutes, researchers have recently made significant progress in designing superhuman artificial intelligence (AI) in no-limit Texas hold'em (NLTH), the primary testbed for large-scale imperfect-information game research. However, …

Poisoning the Well: Can We Simultaneously Attack a Group of Learning Agents?

2023

Reinforcement Learning's (RL) ubiquity has instigated research on potential threats to its training and deployment. Many works study single-learner training-time attacks that "pre-programme" behavioral triggers into a strategy. However, attacks on collections of learning agents …