no code implementations • 20 Mar 2024 • Huachuan Qiu, Shuai Zhang, Hongliang He, Anqi Li, Zhenzhong Lan
Pornographic content occurring in human-machine interaction dialogues can cause severe side effects for users in open-domain dialogue systems.
no code implementations • 19 Feb 2024 • Anqi Li, Yu Lu, Nirui Song, Shuai Zhang, Lizhi Ma, Zhenzhong Lan
High-quality psychological counseling is crucial for mental health worldwide, and timely evaluation is vital for ensuring its effectiveness.
no code implementations • 18 Feb 2024 • Shuai Zhang, Yu Lu, Junwen Liu, JIA YU, Huachuan Qiu, Yuming Yan, Zhenzhong Lan
With the growing humanlike nature of dialog agents, people are now engaging in extended conversations that can stretch from brief moments to substantial periods of time.
1 code implementation • 25 Jan 2024 • Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu
The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents.
2 code implementations • 24 Jan 2024 • Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, Junxian He
Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications.
1 code implementation • 7 Dec 2023 • Huachuan Qiu, Anqi Li, Lizhi Ma, Zhenzhong Lan
Dialogue systems are increasingly integrated into mental health support to help clients facilitate exploration, gain insight, take action, and ultimately heal themselves.
no code implementations • 19 Nov 2023 • JIA YU, Lichao Zhang, Zijie Chen, Fayu Pan, Miaomiao Wen, Yuming Yan, Fangsheng Weng, Shuai Zhang, Lili Pan, Zhenzhong Lan
Moreover, to foster standardization in the T2I-based fashion design field, we propose a new benchmark comprising multiple datasets for evaluating the performance of fashion design models.
no code implementations • 16 Nov 2023 • Junlei Zhang, Hongliang He, Nirui Song, Shuyuan He, Shuai Zhang, Huachuan Qiu, Anqi Li, Lizhi Ma, Zhenzhong Lan
As Large Language Models (LLMs) are becoming prevalent in various fields, there is an urgent need for improved NLP benchmarks that encompass all the necessary knowledge of individual discipline.
1 code implementation • 30 Oct 2023 • Chiyu Song, Zhanchao Zhou, Jianhao Yan, Yuejiao Fei, Zhenzhong Lan, Yue Zhang
Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models (LLMs).
no code implementations • 12 Oct 2023 • Zijie Chen, Lichao Zhang, Fangsheng Weng, Lili Pan, Zhenzhong Lan
We propose a novel approach that involves rewriting user prompts based a new large-scale text-to-image dataset with over 300k prompts from 3115 users.
1 code implementation • 18 Sep 2023 • Huachuan Qiu, Shuai Zhang, Hongliang He, Anqi Li, Zhenzhong Lan
NSFW (Not Safe for Work) content, in the context of a dialogue, can have severe side effects on users in open-domain dialogue systems.
1 code implementation • 31 Jul 2023 • Huachuan Qiu, Tong Zhao, Anqi Li, Shuai Zhang, Hongliang He, Zhenzhong Lan
Our study reveals that ChatGPT struggles to detect safety categories with detailed safety definitions in a zero- and few-shot paradigm, whereas the fine-tuned model proves to be more suitable.
no code implementations • 27 Jul 2023 • Liang Xu, Anqi Li, Lei Zhu, Hang Xue, Changtai Zhu, Kangkang Zhao, Haonan He, Xuanwei Zhang, Qiyue Kang, Zhenzhong Lan
We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE.
1 code implementation • 17 Jul 2023 • Huachuan Qiu, Shuai Zhang, Anqi Li, Hongliang He, Zhenzhong Lan
We present a systematic analysis of the safety and robustness of LLMs regarding the position of explicit normal instructions, word replacements (verbs in explicit normal instructions, target groups in malicious instructions, cue words for explicit normal instructions), and instruction replacements (different explicit normal instructions).
1 code implementation • 27 Jun 2023 • Anqi Li, Lizhi Ma, Yaling Mei, Hongliang He, Shuai Zhang, Huachuan Qiu, Zhenzhong Lan
Communication success relies heavily on reading participants' reactions.
1 code implementation • 25 May 2023 • Yuejiao Fei, Leyang Cui, Sen yang, Wai Lam, Zhenzhong Lan, Shuming Shi
Grammatical error correction systems improve written communication by detecting and correcting language mistakes.
2 code implementations • 24 May 2023 • Junlei Zhang, Zhenzhong Lan, Junxian He
Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings.
1 code implementation • 12 May 2023 • Hongliang He, Junlei Zhang, Zhenzhong Lan, Yue Zhang
Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings.
1 code implementation • 30 Apr 2023 • Huachuan Qiu, Hongliang He, Shuai Zhang, Anqi Li, Zhenzhong Lan
Furthermore, we implement an expert evaluation and the results demonstrate that the dialogues generated with our proposed method are of higher quality than those generated with other baseline methods.
no code implementations • 7 Mar 2022 • Anqi Li, Jingsong Ma, Lizhi Ma, Pengfei Fang, Hongliang He, Zhenzhong Lan
However, these methods often demand large scale and high quality counseling data, which are difficult to collect.
no code implementations • 23 Nov 2021 • Junlei Zhang, Zhenzhong Lan
The corresponding outputs, two sentence embeddings derived from the same sentence with different dropout masks, can be used to build a positive pair.
3 code implementations • NeurIPS 2021 • Mingjian Zhu, Kai Han, Enhua Wu, Qiulin Zhang, Ying Nie, Zhenzhong Lan, Yunhe Wang
To this end, we propose a novel dynamic-resolution network (DRNet) in which the input resolution is determined dynamically based on each input sample.
1 code implementation • 2 Jun 2021 • Chiyu Song, Hongliang He, Haofei Yu, Pengfei Fang, Leyang Cui, Zhenzhong Lan
The current state-of-the-art ranking methods mainly use an encoding paradigm called Cross-Encoder, which separately encodes each context-candidate pair and ranks the candidates according to their fitness scores.
1 code implementation • EMNLP 2021 • Sharan Narang, Hyung Won Chung, Yi Tay, William Fedus, Thibault Fevry, Michael Matena, Karishma Malkan, Noah Fiedel, Noam Shazeer, Zhenzhong Lan, Yanqi Zhou, Wei Li, Nan Ding, Jake Marcus, Adam Roberts, Colin Raffel
The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption.
no code implementations • 14 Oct 2020 • Qingyang Wu, Zhenzhong Lan, Kun Qian, Jing Gu, Alborz Geramifard, Zhou Yu
Transformers have reached remarkable success in sequence modeling.
no code implementations • 29 Sep 2020 • Nan Ding, Xinjie Fan, Zhenzhong Lan, Dale Schuurmans, Radu Soricut
Models based on the Transformer architecture have achieved better accuracy than the ones based on competing architectures for a large set of tasks.
3 code implementations • COLING 2020 • Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks.
4 code implementations • 5 Mar 2020 • Noam Shazeer, Zhenzhong Lan, Youlong Cheng, Nan Ding, Le Hou
We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation. While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.
48 code implementations • ICLR 2020 • Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks.
Ranked #1 on Natural Language Inference on QNLI
no code implementations • 23 Sep 2019 • Sebastian Goodman, Zhenzhong Lan, Radu Soricut
Neural models for abstractive summarization tend to achieve the best performance in the presence of highly specialized, summarization specific modeling add-ons such as pointer-generator, coverage-modeling, and inferencetime heuristics.
no code implementations • 5 Jul 2017 • Po-Yao Huang, Ye Yuan, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann
We report on CMU Informedia Lab's system used in Google's YouTube 8 Million Video Understanding Challenge.
3 code implementations • 2 Apr 2017 • Yi Zhu, Zhenzhong Lan, Shawn Newsam, Alexander G. Hauptmann
State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs.
Ranked #20 on Action Recognition on UCF101
no code implementations • 8 Feb 2017 • Yi Zhu, Zhenzhong Lan, Shawn Newsam, Alexander G. Hauptmann
We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data.
no code implementations • 25 Jan 2017 • Zhenzhong Lan, Yi Zhu, Alexander G. Hauptmann
We investigate the problem of representing an entire video using CNN features for human action recognition.
no code implementations • 17 Jun 2016 • Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
no code implementations • 11 Dec 2015 • Zhenzhong Lan, Shoou-I Yu, Alexander G. Hauptmann
We propose two well-motivated ranking-based methods to enhance the performance of current state-of-the-art human activity recognition systems.
no code implementations • 16 Nov 2015 • Zhenzhong Lan, Shoou-I Yu, Ming Lin, Bhiksha Raj, Alexander G. Hauptmann
We approach this problem by first showing that local handcrafted features and Convolutional Neural Networks (CNNs) share the same convolution-pooling network structure.
no code implementations • 15 Oct 2015 • Zhenzhong Lan, Alexander G. Hauptmann
We address the problem of generating video features for action recognition.
no code implementations • 17 May 2015 • Zhenzhong Lan, Dezhong Yao, Ming Lin, Shoou-I Yu, Alexander Hauptmann
First, we propose a two-stream Stacked Convolutional Independent Subspace Analysis (ConvISA) architecture to show that unsupervised learning methods can significantly boost the performance of traditional local features extracted from data-independent models.
1 code implementation • 12 Mar 2015 • Zhiyong Cheng, Daniel Soudry, Zexi Mao, Zhenzhong Lan
In this paper, we investigate the capability of BMNNs using the EBP algorithm on multiclass image classification tasks.
no code implementations • 13 Feb 2015 • Zhenzhong Lan, Xuanchong Li, Ming Lin, Alexander G. Hauptmann
Therefore, they need to occur frequently enough in the videos and to be be able to tell the difference among different types of motions.
no code implementations • NeurIPS 2014 • Lu Jiang, Deyu Meng, Shoou-I Yu, Zhenzhong Lan, Shiguang Shan, Alexander Hauptmann
Self-paced learning (SPL) is a recently proposed learning regime inspired by the learning process of humans and animals that gradually incorporates easy to more complex samples into training.
no code implementations • CVPR 2015 • Zhenzhong Lan, Ming Lin, Xuanchong Li, Alexander G. Hauptmann, Bhiksha Raj
MIFS compensates for information lost from using differential operators by recapturing information at coarse scales.
no code implementations • 29 Aug 2014 • Zhenzhong Lan, Xuanchong Li, Alexandar G. Hauptmann
To achieve temporal scale invariance, we develop a method called temporal scale pyramid (TSP).