Search Results for author: Haitao Xu

Found 6 papers, 2 papers with code

Struggle with Adversarial Defense? Try Diffusion

1 code implementation12 Apr 2024 Yujie Li, Yanbin Wang, Haitao Xu, Bin Liu, Jianguo Sun, Zhenhao Guo, Wenrui Ma

Unlike data-driven classifiers, TMDC, guided by Bayesian principles, utilizes the conditional likelihood from diffusion models to determine the class probabilities of input images, thereby insulating against the influences of data shift and the limitations of adversarial training.

Adversarial Defense Adversarial Robustness

URLBERT:A Contrastive and Adversarial Pre-trained Model for URL Classification

1 code implementation18 Feb 2024 Yujie Li, Yanbin Wang, Haitao Xu, Zhenhao Guo, Zheng Cao, Lun Zhang

To address this gap, this paper introduces URLBERT, the first pre-trained representation learning model applied to a variety of URL classification or detection tasks.

Contrastive Learning Multi-Task Learning +1

SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group Sparsity

no code implementations30 Oct 2023 Haitao Xu, Songwei Liu, Yuyang Xu, Shuai Wang, Jiashi Li, Chenqian Yan, Liangqiang Li, Lean Fu, Xin Pan, Fangmin Chen

Our framework consists of two parts: (a) A fine-grained kernel sparsity schema with a sparsity granularity between structured pruning and unstructured pruning.

Network Pruning

MIME: Mutual Information Minimisation Exploration

no code implementations16 Jan 2020 Haitao Xu, Brendan McCane, Lech Szymanski, Craig Atkinson

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn.

Montezuma's Revenge reinforcement-learning +2

VASE: Variational Assorted Surprise Exploration for Reinforcement Learning

no code implementations31 Oct 2019 Haitao Xu, Brendan McCane, Lech Szymanski

Exploration in environments with continuous control and sparse rewards remains a key challenge in reinforcement learning (RL).

continuous-control Continuous Control +5

Cannot find the paper you are looking for? You can Submit a new open access paper.