no code implementations • 7 Mar 2024 • Jiatong Li, Wei Liu, Zhihao Ding, Wenqi Fan, Yuqiang Li, Qing Li
Large Language Models (LLMs) have demonstrated exceptional performance in biochemical tasks, especially the molecule caption translation task, which aims to bridge the gap between molecules and natural language texts.
no code implementations • 10 Feb 2024 • Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Dongzhan Zhou, Shufei Zhang, Mao Su, Hansen Zhong, Yuqiang Li, Wanli Ouyang
ChemLLM beats GPT-3. 5 on all three principal tasks in chemistry, i. e., name conversion, molecular caption, and reaction prediction, and surpasses GPT-4 on two of them.
1 code implementation • 17 Oct 2023 • Lin Wang, Wenqi Fan, Jiatong Li, Yao Ma, Qing Li
The rapid development of Internet technology has given rise to a vast amount of graph-structured data.
no code implementations • 19 Sep 2023 • Junzhe Jiang, Shang Qu, Mingyue Cheng, Qi Liu, Zhiding Liu, Hao Zhang, Rujiao Zhang, Kai Zhang, Rui Li, Jiatong Li, Min Gao
Recommender systems are indispensable in the realm of online applications, and sequential recommendation has enjoyed considerable prevalence due to its capacity to encapsulate the dynamic shifts in user interests.
1 code implementation • ICCV 2023 • Yuting Wang, Velibor Ilic, Jiatong Li, Branislav Kisacanin, Vladimir Pavlovic
In this work, we propose ALWOD, a new framework that addresses this problem by fusing active learning (AL) with weakly and semi-supervised object detection paradigms.
no code implementations • 8 Sep 2023 • Jiatong Li, Rui Li, Qi Liu
Existing LLM evaluation methods are mainly supervised signal-based which depends on static datasets and cannot evaluate the ability of LLMs in dynamic real-world scenarios where deep interaction widely exists.
no code implementations • 1 Sep 2023 • Jiatong Li, Qi Liu, Fei Wang, Jiayu Liu, Zhenya Huang, Fangzhou Yao, Linbo Zhu, Yu Su
However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners' cognitive states and the quality of web learning services.
no code implementations • 5 Jul 2023 • Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Zhen Wen, Fei Wang, Xiangyu Zhao, Jiliang Tang, Qing Li
As a result, recent studies have attempted to harness the power of LLMs to enhance recommender systems.
1 code implementation • 11 Jun 2023 • Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, Qing Li
Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs.
Ranked #3 on Text-based de novo Molecule Generation on ChEBI-20
1 code implementation • 3 Jun 2023 • Lea Frermann, Jiatong Li, Shima Khanehzar, Gosia Mikolajczak
Despite increasing interest in the automatic detection of media frames in NLP, the problem is typically simplified as single-label classification and adopts a topic-like view on frames, evading modelling the broader document-level narrative.
1 code implementation • 6 Feb 2023 • Chengyi Liu, Wenqi Fan, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li
Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years.
no code implementations • 23 Oct 2022 • Qinghua Mao, Jiatong Li, Kui Meng
In this paper, we propose a neural-based approach to perform semantic augmentation using external knowledge from search engine for Chinese NER.
Chinese Named Entity Recognition named-entity-recognition +2
1 code implementation • 30 Sep 2022 • Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Junzhe Zhang
This paper studies the problem of learning the shape given in the form of point clouds by inverse sketch-and-extrude.
no code implementations • 1 Sep 2022 • Jiatong Li, Bin He, Fei Mi
In order to expand the information that PLMs can utilize, we encode topic and dialogue history information using certain prompts with multiple channels of Fusion-in-Decoder (FiD) and explore the influence of three different channel settings.
no code implementations • 16 Sep 2021 • Jiatong Li, Kui Meng
In this paper, we propose a new method, Multi-Feature Fusion Embedding for Chinese Named Entity Recognition (MFE-NER), to strengthen the language pattern of Chinese and handle the character substitution problem in Chinese Named Entity Recognition.
Chinese Named Entity Recognition named-entity-recognition +2
1 code implementation • ICCV 2021 • Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Haiyong Jiang, Zhongang Cai, Junzhe Zhang, Liang Pan, Mingyuan Zhang, Haiyu Zhao, Shuai Yi
Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem.
1 code implementation • NeurIPS 2021 • Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, Tongliang Liu
Instead of the early stopping, which trains a whole DNN all at once, we initially train former DNN layers by optimizing the DNN with a relatively large number of epochs.
Ranked #8 on Learning with noisy labels on CIFAR-10N-Aggregate
no code implementations • 28 Feb 2021 • Harold D. Chiang, Jiatong Li, Yuya Sasaki
This paper proposes a novel method of algorithmic subsampling (data sketching) for multiway cluster dependent data.
1 code implementation • 4 Feb 2021 • Hai X. Pham, Ricardo Guerrero, Jiatong Li, Vladimir Pavlovic
Despite the abundance of multi-modal data, such as image-text pairs, there has been little effort in understanding the individual entities and their different roles in the construction of these data instances.
no code implementations • 2 Dec 2020 • Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Jiankang Deng, Jiatong Li, Yinian Mao
The traditional transition matrix is limited to model closed-set label noise, where noisy training data has true class labels within the noisy label set.
no code implementations • 17 Oct 2020 • Jiatong Li, Fangda Han, Ricardo Guerrero, Vladimir Pavlovic
Increased awareness of the impact of food consumption on health and lifestyle today has given rise to novel data-driven food analysis systems.
no code implementations • 26 Sep 2019 • Jiatong Li, Ricardo Guerrero, Vladimir Pavlovic
In this paper, we study the novel problem of not only predicting ingredients from a food image, but also predicting the relative amounts of the detected ingredients.
no code implementations • NAACL 2019 • Jiatong Li, Kai Zheng, Hua Xu, Qiaozhu Mei, Yue Wang
When developing topic classifiers for real-world applications, we begin by defining a set of meaningful topic labels.
no code implementations • 12 May 2017 • Yuqi Han, Chenwei Deng, Zengshuo Zhang, Jiatong Li, Baojun Zhao
Robust feature representation plays significant role in visual tracking.