DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion

1 code implementation • 16 Apr 2024 • Yu Li, Zhihua Wei, Han Jiang, Chuanyang Gong

In this paper, we propose DeStein, a novel method that detoxififies LMs by altering their internal representations in the activation space with lower resource and time cost.

Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning

no code implementations • 1 Apr 2024 • Jian Jiao, Yu Dai, Hefei Mei, Heqian Qiu, Chuanyang Gong, Shiyuan Tang, Xinpeng Hao, Hongliang Li

So we propose SNRO, which slightly shifts the features of new classes to remember old classes.

Class Incremental Learning Incremental Learning

DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction

no code implementations • 16 Apr 2019 • Yeqi Liu, Chuanyang Gong, Ling Yang, Yingyi Chen

The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at different times and the long-term dependence of the temporal relationships between different series.

Time Series Time Series Prediction

Real time expert system for anomaly detection of aerators based on computer vision technology and existing surveillance cameras

no code implementations • 9 Oct 2018 • Yeqi Liu, Yingyi Chen, Huihui Yu, Xiaomin Fang, Chuanyang Gong

To tackle these aforementioned challenges, we propose a real-time expert system based on computer vision technology and existing surveillance cameras for anomaly detection of aerators, which consists of two modules, i. e., object region detection and working state detection.

Anomaly Detection Cultural Vocal Bursts Intensity Prediction +4