1 code implementation • EMNLP 2021 • Yun Ma, Yangbin Chen, Xudong Mao, Qing Li
In this paper, we propose a collaborative learning framework for unsupervised text style transfer using a pair of bidirectional decoders, one decoding from left to right while the other decoding from right to left.
1 code implementation • EMNLP 2021 • Yun Ma, Qing Li
In this paper, we explore Non-AutoRegressive (NAR) decoding for unsupervised text style transfer.
no code implementations • EMNLP 2020 • Xinhong Chen, Qing Li, JianPing Wang
The causal relationships between emotions and causes in text have recently received a lot of attention.
no code implementations • EMNLP 2020 • Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li
Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks.
no code implementations • 12 Jun 2025 • Yilin Xiao, Chuang Zhou, Qinggang Zhang, Bo Li, Qing Li, Xiao Huang
Large language models (LLMs) often struggle with knowledge-intensive tasks due to a lack of background knowledge and a tendency to hallucinate.
no code implementations • 11 Jun 2025 • Jiangyong Huang, Xiaojian Ma, Xiongkun Linghu, Yue Fan, Junchao He, Wenxin Tan, Qing Li, Song-Chun Zhu, Yixin Chen, Baoxiong Jia, Siyuan Huang
A key obstacle to developing 3D-VL generalists lies in data scalability, hindered by the lack of an efficient scene representation.
1 code implementation • 9 Jun 2025 • Wenxin Tang, Jingyu Xiao, Wenxuan Jiang, Xi Xiao, Yuhang Wang, Xuxin Tang, Qing Li, Yuehe Ma, Junliang Liu, Shisong Tang, Michael R. Lyu
Manual slide creation is labor-intensive and requires expert prior knowledge.
no code implementations • 5 Jun 2025 • Tianxu Wang, Zhuofan Zhang, Ziyu Zhu, Yue Fan, Jing Xiong, Pengxiang Li, Xiaojian Ma, Qing Li
However, grounding referring expressions beyond objects in 3D scenes remains unexplored.
no code implementations • 31 May 2025 • Jiahui Geng, Fengyu Cai, Shaobo Cui, Qing Li, LiangWei Chen, Chenyang Lyu, Haonan Li, Derui Zhu, Walter Pretschner, Heinz Koeppl, Fakhri Karray
Using CoQuIR, we benchmark 23 retrieval models, covering both open-source and proprietary systems, and find that even top-performing models frequently fail to distinguish buggy or insecure code from their more robust counterparts.
1 code implementation • 30 May 2025 • Kailin Jiang, Yuntao Du, Yukai Ding, Yuchen Ren, Ning Jiang, Zhi Gao, Zilong Zheng, Lei Liu, Bin Li, Qing Li
Previous work focused on constructing textual knowledge datasets and exploring knowledge injection in LLMs, lacking exploration of multimodal evolving knowledge injection in LMMs.
no code implementations • 29 May 2025 • Zeyu Liu, Yuhang Liu, Guanghao Zhu, Congkai Xie, Zhen Li, Jianbo Yuan, Xinyao Wang, Qing Li, Shing-Chi Cheung, Shengyu Zhang, Fei Wu, Hongxia Yang
Recent advancements in large language models (LLMs) have demonstrated substantial progress in reasoning capabilities, such as DeepSeek-R1, which leverages rule-based reinforcement learning to enhance logical reasoning significantly.
1 code implementation • 26 May 2025 • Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray
In this paper, we introduce the concept of $\textit{safety calibration}$, which systematically addresses both undersafety and oversafety.
1 code implementation • 24 May 2025 • Wentao Hu, WengYu Zhang, Yiyang Jiang, Chen Jason Zhang, XiaoYong Wei, Qing Li
Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a phenomenon we term Hallucination on Hallucination.
no code implementations • 24 May 2025 • Guanghao Meng, Sunan He, Jinpeng Wang, Tao Dai, Letian Zhang, Jieming Zhu, Qing Li, Gang Wang, Rui Zhang, Yong Jiang
To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries.
no code implementations • 24 May 2025 • Qing Li, Runze Gan, James R. Hopgood, Michael E. Davies, Simon J. Godsill
In this paper, we present a novel distributed expectation propagation algorithm for multiple sensors, multiple objects tracking in cluttered environments.
no code implementations • 21 May 2025 • Xintong Zhang, Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaowen Zhang, Yang Liu, Tao Yuan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks.
1 code implementation • 20 May 2025 • Zhenyu Bao, Qing Li, Guibiao Liao, Zhongyuan Zhao, Kanglin Liu
The rigid deformation is applied to the motion-related 3DGs for modeling the dynamic, and the attention-based optimization on the motion-related 3DGs enables the reconstruction of the emerging objects.
no code implementations • 20 May 2025 • Zhicheng Chen, Shibo Feng, Xi Xiao, Zhong Zhang, Qing Li, Xingyu Gao, Peilin Zhao
MSDformer employs a multi-scale time series tokenizer to learn discrete token representations at multiple scales, which jointly characterize the complex nature of time series data.
no code implementations • 17 May 2025 • Yunqing Liu, Wenqi Fan, XiaoYong Wei, Qing Li
We argue that the structural information of proteins is not only limited to their 3D information but also encompasses information from amino acid molecules (local information) to protein-protein structure similarity (global information).
no code implementations • 15 May 2025 • Jun Guo, Xiaojian Ma, Yikai Wang, Min Yang, Huaping Liu, Qing Li
This paper investigates training better visual world models for robot manipulation, i. e., models that can predict future visual observations by conditioning on past frames and robot actions.
no code implementations • 14 May 2025 • Dayong Liang, Changmeng Zheng, Zhiyuan Wen, Yi Cai, Xiao-Yong Wei, Qing Li
Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes.
1 code implementation • 10 May 2025 • Dawei Huang, Qing Li, Chuan Yan, Zebang Cheng, Yurong Huang, Xiang Li, Bin Li, Xiaohui Wang, Zheng Lian, Xiaojiang Peng
While Large Multimodal Models (LMMs) have demonstrated significant progress in general vision-language (VL) tasks, their performance in emotion-specific scenarios remains limited.
no code implementations • CVPR 2025 • Huangyue Yu, Baoxiong Jia, Yixin Chen, Yandan Yang, Puhao Li, Rongpeng Su, Jiaxin Li, Qing Li, Wei Liang, Song-Chun Zhu, Tengyu Liu, Siyuan Huang
Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization.
no code implementations • 30 Apr 2025 • Pengxiang Li, Zhi Gao, Bofei Zhang, Yapeng Mi, Xiaojian Ma, Chenrui Shi, Tao Yuan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent.
1 code implementation • Briefings in Bioinformatics 2025 • WengYu Zhang, Qi Tian, Yi Cao, Wenqi Fan, Dongmei Jiang, YaoWei Wang, Qing Li, Xiao-Yong Wei
The accurate categorization of compounds within the anatomical therapeutic chemical (ATC) system is fundamental for drug development and fundamental research.
Ranked #1 on
Drug ATC Classification
on ATC-SMILES
no code implementations • 22 Apr 2025 • Kun Wang, Guibin Zhang, Zhenhong Zhou, Jiahao Wu, Miao Yu, Shiqian Zhao, Chenlong Yin, Jinhu Fu, Yibo Yan, Hanjun Luo, Liang Lin, Zhihao Xu, Haolang Lu, Xinye Cao, Xinyun Zhou, Weifei Jin, Fanci Meng, Shicheng Xu, Junyuan Mao, Yu Wang, Hao Wu, Minghe Wang, Fan Zhang, Junfeng Fang, Wenjie Qu, Yue Liu, Chengwei Liu, Yifan Zhang, Qiankun Li, Chongye Guo, Yalan Qin, Zhaoxin Fan, Kai Wang, Yi Ding, Donghai Hong, Jiaming Ji, Yingxin Lai, Zitong Yu, Xinfeng Li, Yifan Jiang, Yanhui Li, Xinyu Deng, Junlin Wu, Dongxia Wang, Yihao Huang, Yufei Guo, Jen-tse Huang, Qiufeng Wang, Xiaolong Jin, Wenxuan Wang, Dongrui Liu, Yanwei Yue, Wenke Huang, Guancheng Wan, Heng Chang, Tianlin Li, Yi Yu, Chenghao Li, Jiawei Li, Lei Bai, Jie Zhang, Qing Guo, Jingyi Wang, Tianlong Chen, Joey Tianyi Zhou, Xiaojun Jia, Weisong Sun, Cong Wu, Jing Chen, Xuming Hu, Yiming Li, Xiao Wang, Ningyu Zhang, Luu Anh Tuan, Guowen Xu, Jiaheng Zhang, Tianwei Zhang, Xingjun Ma, Jindong Gu, Liang Pang, Xiang Wang, Bo An, Jun Sun, Mohit Bansal, Shirui Pan, Lingjuan Lyu, Yuval Elovici, Bhavya Kailkhura, Yaodong Yang, Hongwei Li, Wenyuan Xu, Yizhou Sun, Wei Wang, Qing Li, Ke Tang, Yu-Gang Jiang, Felix Juefei-Xu, Hui Xiong, XiaoFeng Wang, DaCheng Tao, Philip S. Yu, Qingsong Wen, Yang Liu
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
1 code implementation • 17 Apr 2025 • Bofei Zhang, Zirui Shang, Zhi Gao, Wang Zhang, Rui Xie, Xiaojian Ma, Tao Yuan, Xinxiao wu, Song-Chun Zhu, Qing Li
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks.
no code implementations • 16 Apr 2025 • Zeyu Dai, Shengcai Liu, Rui He, Jiahao Wu, Ning Lu, Wenqi Fan, Qing Li, Ke Tang
In light of this, we propose SemDiff, a novel unrestricted adversarial attack that explores the semantic latent space of diffusion models for meaningful attributes, and devises a multi-attributes optimization approach to ensure attack success while maintaining the naturalness and imperceptibility of generated UAEs.
no code implementations • 15 Apr 2025 • Liangbo Ning, Wenqi Fan, Qing Li
Specifically, we introduce an LLM-based poison scanner to detect the poisoned items by leveraging the powerful language understanding and rich knowledge of LLMs.
no code implementations • 13 Apr 2025 • Liang-bo Ning, Shijie Wang, Wenqi Fan, Qing Li, Xin Xu, Hao Chen, Feiran Huang
Recently, Large Language Model (LLM)-empowered recommender systems (RecSys) have brought significant advances in personalized user experience and have attracted considerable attention.
no code implementations • 5 Apr 2025 • Zihuai Zhao, Wenqi Fan, Yao Wu, Qing Li
Large Language Models (LLMs) have demonstrated unprecedented language understanding and reasoning capabilities to capture diverse user preferences and advance personalized recommendations.
no code implementations • 3 Apr 2025 • Liangbo Ning, Wenqi Fan, Qing Li
Recently, Large Language Model (LLM)-empowered recommender systems have revolutionized personalized recommendation frameworks and attracted extensive attention.
no code implementations • 30 Mar 2025 • Liangbo Ning, Ziran Liang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Wenqi Fan, Xiao-Yong Wei, Shanru Lin, Hui Liu, Philip S. Yu, Qing Li
With the advancement of web techniques, they have significantly revolutionized various aspects of people's lives.
1 code implementation • CVPR 2025 • Jiangyong Huang, Baoxiong Jia, Yan Wang, Ziyu Zhu, Xiongkun Linghu, Qing Li, Song-Chun Zhu, Siyuan Huang
Our evaluation of state-of-the-art 3D-VL models on Beacon3D reveals that (i) object-centric evaluation elicits true model performance and particularly weak generalization in QA; (ii) grounding-QA coherence remains fragile in current 3D-VL models, and (iii) incorporating large language models (LLMs) to 3D-VL models, though as a prevalent practice, hinders grounding capabilities and has yet to elevate QA capabilities.
no code implementations • CVPR 2025 • Guibiao Liao, Qing Li, Zhenyu Bao, Guoping Qiu, Kanglin Liu
However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse distribution of Gaussian points and insufficient view supervision.
no code implementations • 16 Mar 2025 • Qing Li, Jiahui Geng, Derui Zhu, Fengyu Cai, Chenyang Lyu, Fakhri Karray
To address this issue, we introduce SAUCE, a novel method that leverages sparse autoencoders (SAEs) for fine-grained and selective concept unlearning in VLMs.
no code implementations • 13 Mar 2025 • Bolin Chen, Baoquan Zhao, Haoran Xie, Yi Cai, Qing Li, Xudong Mao
In this paper, we comprehensively analyze the limitations of the standard diffusion parameterization, which learns to predict noise, in the context of style transfer.
1 code implementation • 12 Mar 2025 • Jiani Huang, Shijie Wang, Liang-bo Ning, Wenqi Fan, Shuaiqiang Wang, Dawei Yin, Qing Li
To address this gap, we introduce RecBench+, a new dataset benchmark designed to access LLMs' ability to handle intricate user recommendation needs in the era of LLMs.
no code implementations • 10 Mar 2025 • Kexin Di, Xiuxing Li, Yuyang Han, Ziyu Li, Qing Li, Xia Wu
Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge.
1 code implementation • CVPR 2025 • Haitao Wu, Qing Li, Changqing Zhang, Zhen He, Xiaomin Ying
When encoded brain representations are directly aligned with the corresponding pretrained image features, the System GAP and Random GAP between paired data challenge the model, requiring it to bridge these gaps.
1 code implementation • 5 Mar 2025 • Fanwen Wang, Zi Wang, Yan Li, Jun Lyu, Chen Qin, Shuo Wang, Kunyuan Guo, Mengting Sun, Mingkai Huang, Haoyu Zhang, Michael Tänzer, Qirong Li, Xinran Chen, Jiahao Huang, Yinzhe Wu, Kian Anvari Hamedani, Yuntong Lyu, Longyu Sun, Qing Li, Ziqiang Xu, Bingyu Xin, Dimitris N. Metaxas, Narges Razizadeh, Shahabedin Nabavi, George Yiasemis, Jonas Teuwen, Zhenxi Zhang, Sha Wang, Chi Zhang, Daniel B. Ennis, Zhihao Xue, Chenxi Hu, Ruru Xu, Ilkay Oksuz, Donghang Lyu, Yanxin Huang, Xinrui Guo, Ruqian Hao, Jaykumar H. Patel, Guanke Cai, Binghua Chen, Yajing Zhang, Sha Hua, Zhensen Chen, Qi Dou, Xiahai Zhuang, Qian Tao, Wenjia Bai, Jing Qin, He Wang, Claudia Prieto, Michael Markl, Alistair Young, Hao Li, Xihong Hu, Lianmin Wu, Xiaobo Qu, Guang Yang, Chengyan Wang
In addition, through a detailed analysis of the results submitted to the challenge, we have also made several findings, including: 1) adaptive prompt-learning embedding is an effective means for achieving strong generalization in reconstruction models; 2) enhanced data consistency based on physics-informed networks is also an effective pathway toward a universal model; 3) traditional evaluation metrics have limitations when assessing ground-truth references with moderate or lower image quality, highlighting the need for subjective evaluation methods.
no code implementations • 4 Mar 2025 • Ziang Zhou, Tianyuan Jin, Jieming Shi, Qing Li
Large Language Models (LLMs) often exhibit misaligned confidence scores, usually overestimating the reliability of their predictions.
no code implementations • 4 Mar 2025 • Ruizhi Zhang, Shengfeng Zhu, Kan Wang, Ding She, Jean-Philippe Argaud, Bertrand Bouriquet, Qing Li, Helin Gong
Reactor physics is the study of neutron properties, focusing on using models to examine the interactions between neutrons and materials in nuclear reactors.
1 code implementation • 27 Feb 2025 • Yuntao Du, Kailin Jiang, Zhi Gao, Chenrui Shi, Zilong Zheng, Siyuan Qi, Qing Li
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining from scratch.
no code implementations • 25 Feb 2025 • Sirui Huang, Hanqian Li, Yanggan Gu, Xuming Hu, Qing Li, Guandong Xu
Given that substantial amounts of domain-specific knowledge are stored in structured formats, such as web data organized through HTML, Large Language Models (LLMs) are expected to fully comprehend this structured information to broaden their applications in various real-world downstream tasks.
no code implementations • 22 Feb 2025 • Fucheng Guo, Zeyu Luan, Qing Li, Dan Zhao, Yong Jiang
Federated Learning (FL) has emerged as an essential framework for distributed machine learning, especially with its potential for privacy-preserving data processing.
no code implementations • 22 Feb 2025 • Jiahui Geng, Qing Li, Herbert Woisetschlaeger, Zongxiong Chen, Yuxia Wang, Preslav Nakov, Hans-Arno Jacobsen, Fakhri Karray
This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}.
no code implementations • 20 Feb 2025 • Xu-Lu Zhang, Zhen-Qun Yang, Dong-Mei Jiang, Ga Liao, Qing Li, Ramesh Jain, Xiao-Yong Wei
This is accomplished using a collocative learning framework in which 1) we construct collocative tensors as pseudo-images from 1D ECG signals to improve the feasibility of 2D image-based deep models; 2) we formulate the cardiac logic of analyzing the ECG data in a comparative way as periodic attention regulators so as to guide the deep inference to collect evidence in a human comprehensible manner; and 3) we improve the interpretability of the framework by enabling the backtracking of evidence with a set of methods designed for Class Activation Mapping (CAM) decoding and decision tree/forest generation.
no code implementations • 18 Feb 2025 • Tianyi Zhang, WengYu Zhang, Xulu Zhang, Jiaxin Wu, Xiao-Yong Wei, Jiannong Cao, Qing Li
Accurate human localization is crucial for various applications, especially in the Metaverse era.
no code implementations • 18 Feb 2025 • Guanyuan Yu, Qing Li, Yu Zhao, Jun Wang, Yijun Chen, Shaolei Chen
Our approach represents a significant advancement in leveraging artificial intelligence to enhance financial stability, offering a powerful solution to mitigate the spread of risks within financial networks.
no code implementations • 18 Feb 2025 • Zheng Yuan, Hao Chen, Zijin Hong, Qinggang Zhang, Feiran Huang, Qing Li, Xiao Huang
Extensive experiments on Spider and BIRD benchmarks verify that KaSLA can significantly improve the SQL generation performance of SOTA Text2SQL models by substituting their schema linking processes.
1 code implementation • 16 Feb 2025 • Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Qing Li, Lei Chen
Large Language Models (LLMs) have demonstrated impressive capabilities in natural language processing tasks, such as text generation and semantic understanding.
no code implementations • 14 Feb 2025 • Xulu Zhang, XiaoYong Wei, Jinlin Wu, Jiaxin Wu, Zhaoxiang Zhang, Zhen Lei, Qing Li
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities.
1 code implementation • 13 Feb 2025 • Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang
By treating LLMs as knowledge databases, we translate malicious queries in natural language into structured non-natural query language to bypass the safety alignment mechanisms of LLMs.
no code implementations • 12 Feb 2025 • Junpeng Zhang, Lei Cheng, Qing Li, Liang Lin, Quanshi Zhang
In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power.
no code implementations • 4 Feb 2025 • Hongxin Li, Jingfan Chen, Jingran Su, Yuntao Chen, Qing Li, Zhaoxiang Zhang
In this work, we propose the \methodname{} pipeline for automatically annotating UI elements with detailed functionality descriptions at scale.
no code implementations • 4 Feb 2025 • Xiangzhi Eric Wang, Zackary P. T. Sin, Ye Jia, Daniel Archer, Wynonna H. Y. Fong, Qing Li, Chen Li
In our daily lives, we can naturally convey instructions for the spatial manipulation of objects using words and gestures.
1 code implementation • 1 Feb 2025 • Yuan Gao, Hao Wu, Ruiqi Shu, Huanshuo Dong, Fan Xu, Rui Ray Chen, Yibo Yan, Qingsong Wen, Xuming Hu, Kun Wang, Jiahao Wu, Qing Li, Hui Xiong, Xiaomeng Huang
Accurate weather forecasts are important for disaster prevention, agricultural planning, etc.
no code implementations • 31 Jan 2025 • Zhiyao Xu, Dan Zhao, Qingsong Zou, Jingyu Xiao, Yong Jiang, Zhenhui Yuan, Qing Li
In this paper, we propose an LLM-based synthetic dataset generation IoTGen framework to enhance the generalization of downstream smart home intelligent models.
no code implementations • 27 Jan 2025 • Wenna Lai, Haoran Xie, Guandong Xu, Qing Li
The most challenging task, aspect sentiment quad prediction (ASQP), predicts these elements simultaneously, hindered by difficulties in accurately coupling different sentiment elements.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
no code implementations • 24 Jan 2025 • Qing Li, Jiahui Geng, Zongxiong Chen, Kun Song, Lei Ma, Fakhri Karray
Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs).
no code implementations • 17 Jan 2025 • Wenqi Fan, Yi Zhou, Shijie Wang, Yuyao Yan, Hui Liu, Qian Zhao, Le Song, Qing Li
As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems.
no code implementations • 9 Jan 2025 • Rujie Wu, Xiaojian Ma, Hai Ci, Yue Fan, Yuxuan Wang, Haozhe Zhao, Qing Li, Yizhou Wang
Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4. 6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.)).
1 code implementation • 5 Jan 2025 • Haozhen Zhang, Haodong Yue, Xi Xiao, Le Yu, Qing Li, Zhen Ling, Ye Zhang
With the growing significance of network security, the classification of encrypted traffic has emerged as an urgent challenge.
1 code implementation • 5 Jan 2025 • Lin Wang, Qing Li
To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation.
1 code implementation • 3 Jan 2025 • Lin Wang, Weisong Wang, Xuanji Xiao, Qing Li
To mitigate noise propagation in graph data and extract reliable social interests, we introduce a dual-view denoising framework.
no code implementations • 1 Jan 2025 • Haoyang Li, Yuming Xu, Chen Jason Zhang, Alexander Zhou, Lei Chen, Qing Li
Graph-level tasks, which predict properties or classes for the entire graph, are critical for applications, such as molecular property prediction and subgraph counting.
no code implementations • 31 Dec 2024 • Yue Fan, Xiaojian Ma, Rongpeng Su, Jun Guo, Rujie Wu, Xi Chen, Qing Li
This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI.
1 code implementation • 27 Dec 2024 • Haoyang Li, Yiming Li, Anxin Tian, Tianhao Tang, Zhanchao Xu, Xuejia Chen, Nicole Hu, Wei Dong, Qing Li, Lei Chen
This survey provides a comprehensive overview of KV cache management strategies for LLM acceleration, categorizing them into token-level, model-level, and system-level optimizations.
no code implementations • 20 Dec 2024 • Jiaxin Wu, Chong-Wah Ngo, Xiao-Yong Wei, Qing Li
The generated queries retrieve different rank lists from the original query.
no code implementations • 20 Dec 2024 • Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma, Tao Yuan, Yue Fan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks.
no code implementations • 20 Dec 2024 • Jiaxin Wu, WengYu Zhang, Xiao-Yong Wei, Qing Li
In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for video content.
no code implementations • 20 Dec 2024 • Jiaxin Wu, Yiyang Jiang, Xiao-Yong Wei, Qing Li
Specifically, we provide the video captions generated by the LLaVA-Next-Video model and the video subtitles with timestamps as context, and ask GPT4 to generate step captions for the given medical query.
1 code implementation • 20 Dec 2024 • Chengyi Liu, Jiahao Zhang, Shijie Wang, Wenqi Fan, Qing Li
With the prevalence of social networks on online platforms, social recommendation has become a vital technique for enhancing personalized recommendations.
1 code implementation • 19 Dec 2024 • Jiatong Li, Junxian Li, Yunqing Liu, Dongzhan Zhou, Qing Li
In this paper, we propose Text-based Open Molecule Generation Benchmark (TOMG-Bench), the first benchmark to evaluate the open-domain molecule generation capability of LLMs.
Ranked #1 on
Description-guided molecule generation
on TOMG-Bench
no code implementations • 15 Dec 2024 • Ziang Zhou, Zhihao Ding, Jieming Shi, Qing Li, Shiqi Shen
In this paper, we present TINED, a novel approach that distills GNNs to MLPs on a layer-by-layer basis using Teacher Injection and Dirichlet Energy Distillation techniques.
no code implementations • 12 Dec 2024 • Wenna Lai, Haoran Xie, Guandong Xu, Qing Li
Implicit sentiment analysis (ISA) presents significant challenges due to the absence of salient cue words.
1 code implementation • 8 Dec 2024 • Jiali Chen, Xusen Hei, Yuqi Xue, Yuancheng Wei, Jiayuan Xie, Yi Cai, Qing Li
Large multimodal models (LMMs) have shown remarkable performance in the visual commonsense reasoning (VCR) task, which aims to answer a multiple-choice question based on visual commonsense within an image.
no code implementations • arXiv preprint 2024 • Jiatong Li, Yunqing Liu, Wei Liu, Jingdi Lei, Di Zhang, Wenqi Fan, Dongzhan Zhou, Yuqiang Li, Qing Li
Previous endeavours often treat the molecule as a general SMILES string or molecular graph, neglecting the fine-grained alignments between the molecular sub-structures and the descriptive textual phrases, which are crucial for accurate and explainable predictions.
Ranked #2 on
Text-based de novo Molecule Generation
on ChEBI-20
no code implementations • 22 Nov 2024 • Jiatong Li, Yunqing Liu, Wei Liu, Jingdi Le, Di Zhang, Wenqi Fan, Dongzhan Zhou, Yuqiang Li, Qing Li
Previous endeavours often treat the molecule as a general SMILES string or molecular graph, neglecting the fine-grained alignments between the molecular sub-structures and the descriptive textual phrases, which are crucial for accurate and explainable predictions.
1 code implementation • 3 Nov 2024 • Langming Liu, Xiangyu Zhao, Chi Zhang, Jingtong Gao, Wanyu Wang, Wenqi Fan, Yiqi Wang, Ming He, Zitao Liu, Qing Li
Transformer models have achieved remarkable success in sequential recommender systems (SRSs).
1 code implementation • 3 Nov 2024 • Langming Liu, Wanyu Wang, Xiangyu Zhao, Zijian Zhang, Chunxu Zhang, Shanru Lin, Yiqi Wang, Lixin Zou, Zitao Liu, Xuetao Wei, Hongzhi Yin, Qing Li
In user preference modeling, both methods learn local and global models, collaboratively learning users' common and personalized interests under the federated learning setting.
no code implementations • 29 Oct 2024 • Kun Song, Ruben Solozabal, Li Hao, Lu Ren, Moloud Abdar, Qing Li, Fakhri Karray, Martin Takac
To address this issue, we introduce second-order pooling into hyperbolic representation learning, as it naturally increases the distance between samples without compromising the generalization ability of the input features.
no code implementations • 24 Oct 2024 • Huan Cui, Qing Li, Hanling Wang, Yong Jiang
Mobile deep vision systems play a vital role in numerous scenarios.
no code implementations • 24 Oct 2024 • Huan Cui, Qing Li, Hanling Wang, Yong Jiang
We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications.
1 code implementation • 23 Sep 2024 • Ahjol Senbi, Tianyu Huang, Fei Lyu, Qing Li, Yuhui Tao, Wei Shao, Qiang Chen, Chengyan Wang, Shuo Wang, Tao Zhou, Yizhe Zhang
We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images).
no code implementations • 16 Sep 2024 • Wei Wang, Qing Li
So, what is the underlying mechanism of this memory?
no code implementations • 11 Sep 2024 • Qing Li, Jinxing Hua, Qiuxia Sun
In this paper, we propose a Q-learning based decision-making framework to improve the safety and efficiency of Autonomous Vehicles when they encounter other maliciously behaving vehicles while passing through unsignalized intersections.
no code implementations • 2 Sep 2024 • Haoran Yang, Xiangyu Zhao, Sirui Huang, Qing Li, Guandong Xu
Graph Contrastive Learning (GCL) is a potent paradigm for self-supervised graph learning that has attracted attention across various application scenarios.
2 code implementations • 2 Sep 2024 • Haohao Qu, Yifeng Zhang, Liangbo Ning, Wenqi Fan, Qing Li
Sequential recommendation methods are crucial in modern recommender systems for their remarkable capability to understand a user's changing interests based on past interactions.
no code implementations • 28 Aug 2024 • Feize Wu, Yun Pang, Junyi Zhang, Lianyu Pang, Jian Yin, Baoquan Zhao, Qing Li, Xudong Mao
This is based on the insight that appropriate output vectors of the text encoder for the context tokens can only be achieved if the new concept's text embedding is correctly learned.
no code implementations • 27 Aug 2024 • Yuyin Lu, Hegang Chen, Pengbo Mao, Yanghui Rao, Haoran Xie, Fu Lee Wang, Qing Li
Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them.
no code implementations • 24 Aug 2024 • Qing Li, Runze Gan, Simon Godsill
This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges among neighboring sensors.
1 code implementation • 22 Aug 2024 • Sirui Huang, Yanggan Gu, Xuming Hu, Zhonghao Li, Qing Li, Guandong Xu
This benchmark allows us to investigate the capability of LLMs across five factual tasks derived from the unique characteristics of structural facts.
no code implementations • 15 Aug 2024 • Chuyang Ye, Dongyan Wei, Zhendong Liu, Yuanyi Pang, Yixi Lin, Jiarong Liao, Qinting Jiang, Xianghua Fu, Qing Li, Jingyan Jiang
It features three key components: Diversity Discrimination (DD) to assess batch diversity, Diversity Adaptive Batch Normalization (DABN) to tailor normalization methods based on DD insights, and Diversity Adaptive Fine-Tuning (DAFT) to selectively fine-tune the model.
no code implementations • 11 Aug 2024 • Qing Li, Jiahui Geng, Chenyang Lyu, Derui Zhu, Maxim Panov, Fakhri Karray
In particular, we conduct an extensive study on three kinds of techniques: uncertainty-based, consistency-based, and supervised uncertainty quantification methods on four representative LVLMs across two different tasks.
1 code implementation • 10 Aug 2024 • Yiran Li, Gongyao Guo, Jieming Shi, Renchi Yang, Shiqi Shen, Qing Li, Jun Luo
In this paper, we first present AHCKA as an efficient approach to attributed hypergraph clustering (AHC).
no code implementations • 7 Aug 2024 • Zhuofan Zhang, Ziyu Zhu, Pengxiang Li, Tengyu Liu, Xiaojian Ma, Yixin Chen, Baoxiong Jia, Siyuan Huang, Qing Li
Grounding natural language in physical 3D environments is essential for the advancement of embodied artificial intelligence.
no code implementations • 5 Aug 2024 • Tongtong Feng, Qing Li, Xin Wang, Mingzi Wang, Guangyao Li, Wenwu Zhu
For image restoration, MCGF incorporates a shared encoder and a lightweight restoration module to help the backbone eliminate weather-specific information.
no code implementations • 3 Aug 2024 • Liang-bo Ning, Zeyu Dai, Wenqi Fan, Jingran Su, Chao Pan, Luning Wang, Qing Li
Recent studies have shown that adversaries can manipulate the predictions of DNNs by adding a universal adversarial perturbation (UAP) to benign samples.
no code implementations • 2 Aug 2024 • Haohao Qu, Liangbo Ning, Rui An, Wenqi Fan, Tyler Derr, Hui Liu, Xin Xu, Qing Li
In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel.
no code implementations • 1 Aug 2024 • Zhenyu Bao, Guibiao Liao, Kaichen Zhou, Kanglin Liu, Qing Li, Guoping Qiu
To handle these issues, we propose the LoopSparseGS, a loop-based 3DGS framework for the sparse novel view synthesis task.
no code implementations • 31 Jul 2024 • Wei Wang, Qing Li
Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks.
no code implementations • 31 Jul 2024 • Rubing Chen, Xulu Zhang, Jiaxin Wu, Wenqi Fan, Xiao-Yong Wei, Qing Li
We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall.
no code implementations • 30 Jul 2024 • Tianyi Zhang, WengYu Zhang, Xulu Zhang, Jiaxin Wu, Xiao-Yong Wei, Jiannong Cao, Qing Li
Accurate human localization is crucial for various applications, especially in the Metaverse era.
1 code implementation • 21 Jul 2024 • Yiyang Jiang, WengYu Zhang, Xulu Zhang, XiaoYong Wei, Chang Wen Chen, Qing Li
Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings.
Ranked #3 on
Video Grounding
on QVHighlights
no code implementations • 16 Jul 2024 • Pengxiang Li, Zhi Gao, Bofei Zhang, Tao Yuan, Yuwei Wu, Mehrtash Harandi, Yunde Jia, Song-Chun Zhu, Qing Li
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction.
1 code implementation • 7 Jul 2024 • Haozhe Zhao, Xiaojian Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, Baobao Chang
This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing.
Ranked #5 on
Image Editing
on ImgEdit-Data
1 code implementation • 3 Jul 2024 • Jiahao Wu, Ning Lu, Zeiyu Dai, Kun Wang, Wenqi Fan, Shengcai Liu, Qing Li, Ke Tang
However, while existing graph condensation studies mainly focus on the best trade-off between graph size and the GNNs' performance (model utility), they overlook the security issues of graph condensation.
no code implementations • 2 Jul 2024 • Wenna Lai, Haoran Xie, Guandong Xu, Qing Li
To identify implicit sentiment with reliable reasoning, this study proposes RVISA, a two-stage reasoning framework that harnesses the generation ability of DO LLMs and the reasoning ability of ED LLMs to train an enhanced reasoner.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
no code implementations • 2 Jul 2024 • Wei Wang, Qing Li
What is the fundamental difference between residual-based CNNs and Transformer-based networks?
no code implementations • 1 Jul 2024 • Wei Wang, Qing Li
Language models have emerged as a critical area of focus in artificial intelligence, particularly with the introduction of groundbreaking innovations like ChatGPT.
no code implementations • 27 Jun 2024 • ZiHao Wang, Shaofei Cai, Zhancun Mu, Haowei Lin, Ceyao Zhang, Xuejie Liu, Qing Li, Anji Liu, Xiaojian Ma, Yitao Liang
First, we introduce a self-supervised approach to learn a behavior encoder that produces discretized tokens for behavior trajectories $\tau = \{o_0, a_0, \dots\}$ and an imitation learning policy decoder conditioned on these tokens.
1 code implementation • 16 Jun 2024 • Jingyu Xiao, Zhiyao Xu, Qingsong Zou, Qing Li, Dan Zhao, Dong Fang, Ruoyu Li, Wenxin Tang, Kang Li, Xudong Zuo, Penghui Hu, Yong Jiang, Zixuan Weng, Michael R. Lyv
However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors.
no code implementations • 15 Jun 2024 • Haohao Qu, Wenqi Fan, Zihuai Zhao, Qing Li
There is a growing interest in utilizing large-scale language models (LLMs) to advance next-generation Recommender Systems (RecSys), driven by their outstanding language understanding and in-context learning capabilities.
no code implementations • 7 Jun 2024 • Lianyu Pang, Jian Yin, Baoquan Zhao, Feize Wu, Fu Lee Wang, Qing Li, Xudong Mao
We attribute these issues to the incorrect learning of the embedding alignment for the concept.
1 code implementation • 3 Jun 2024 • Xiao Chen, Xudong Jiang, Yunkang Tao, Zhen Lei, Qing Li, Chenyang Lei, Zhaoxiang Zhang
Secondly, we devise a contrastive mask-guided reflection removal network that comprises a newly proposed contrastive guidance interaction block (CGIB).
no code implementations • 30 May 2024 • Zhicheng Chen, Xi Xiao, Ke Xu, Zhong Zhang, Yu Rong, Qing Li, Guojun Gan, Zhiqiang Xu, Peilin Zhao
Multivariate time series prediction is widely used in daily life, which poses significant challenges due to the complex correlations that exist at multi-grained levels.
no code implementations • 29 May 2024 • Xueyao Sun, Kaize Shi, Haoran Tang, Guandong Xu, Qing Li
Large language models (LLMs) can elicit social bias during generations, especially when inference with toxic prompts.
no code implementations • 27 May 2024 • Shengyuan Chen, Qinggang Zhang, Junnan Dong, Wen Hua, Qing Li, Xiao Huang
Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs.
no code implementations • 19 May 2024 • Ziyu Zhu, Zhuofan Zhang, Xiaojian Ma, Xuesong Niu, Yixin Chen, Baoxiong Jia, Zhidong Deng, Siyuan Huang, Qing Li
A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene.
Ranked #10 on
3D Question Answering (3D-QA)
on SQA3D
no code implementations • 16 May 2024 • Junpeng Zhang, Qing Li, Liang Lin, Quanshi Zhang
This paper investigates the dynamics of a deep neural network (DNN) learning interactions.
no code implementations • 10 May 2024 • Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, Qing Li
Given the powerful abilities of RAG in providing the latest and helpful auxiliary information, Retrieval-Augmented Large Language Models (RA-LLMs) have emerged to harness external and authoritative knowledge bases, rather than solely relying on the model's internal knowledge, to augment the generation quality of LLMs.
no code implementations • 9 May 2024 • Xulu Zhang, Xiao-Yong Wei, WengYu Zhang, Jinlin Wu, Zhaoxiang Zhang, Zhen Lei, Qing Li
This paper offers a comprehensive survey of PCS, with a particular focus on the diffusion models.
no code implementations • 6 May 2024 • Kaize Shi, Xueyao Sun, Qing Li, Guandong Xu
The proposed algorithm compresses the cluttered raw retrieved documents into a compact set of crucial concepts distilled from the informative nodes of AMR by referring to reliable linguistic features.
Abstract Meaning Representation
Open-Domain Question Answering
+3
1 code implementation • 3 May 2024 • Ziang Zhou, Jieming Shi, Renchi Yang, Yuanhang Zou, Qing Li
We identify a potential semantic mixing issue in existing message passing processes, where the representations of the neighbors of a node $v$ are forced to be transformed to the feature space of $v$ for aggregation, though the neighbors are in different types.
no code implementations • 23 Apr 2024 • Wenqi Fan, Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li
Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.
1 code implementation • 22 Apr 2024 • Guibiao Liao, Jiankun Li, Zhenyu Bao, Xiaoqing Ye, Jingdong Wang, Qing Li, Kanglin Liu
Additionally, to address the semantic ambiguity, caused by utilizing view-inconsistent 2D CLIP semantics to supervise Gaussians, we introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.
no code implementations • 22 Apr 2024 • Zeyu Li, Ruitong Gan, Chuanchen Luo, Yuxi Wang, Jiaheng Liu, Ziwei Zhu Man Zhang, Qing Li, XuCheng Yin, Zhaoxiang Zhang, Junran Peng
Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance.
1 code implementation • 18 Apr 2024 • Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns.
1 code implementation • 8 Apr 2024 • Sannyuya Liu, Qing Li, Xiaoxuan Shen, Jianwen Sun, Zongkai Yang
Skill acquisition is a key area of research in cognitive psychology as it encompasses multiple psychological processes.
1 code implementation • 6 Apr 2024 • Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz
Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual statements.
1 code implementation • 22 Mar 2024 • Changmeng Zheng, Dayong Liang, WengYu Zhang, Xiao-Yong Wei, Tat-Seng Chua, Qing Li
The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images.
1 code implementation • 22 Mar 2024 • Xulu Zhang, WengYu Zhang, Xiao-Yong Wei, Jinlin Wu, Zhaoxiang Zhang, Zhen Lei, Qing Li
The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept.
no code implementations • 22 Mar 2024 • Jun Guo, Xiaojian Ma, Yue Fan, Huaping Liu, Qing Li
Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, which is based on spatial relationship and need no additional training.
1 code implementation • 19 Mar 2024 • Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li
Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies.
no code implementations • 18 Mar 2024 • Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li
We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos.
1 code implementation • 11 Mar 2024 • Yujuan Ding, Yunshan Ma, Wenqi Fan, Yige Yao, Tat-Seng Chua, Qing Li
Fashion analysis refers to the process of examining and evaluating trends, styles, and elements within the fashion industry to understand and interpret its current state, generating fashion reports.
1 code implementation • 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 • CVPR 2024 • Cong Ma, Lei Qiao, Chengkai Zhu, Kai Liu, Zelong Kong, Qing Li, Xueqi Zhou, Yuheng Kan, Wei Wu
Based on HoloVIC, we formulated four tasks to facilitate the development of related research.
1 code implementation • 22 Feb 2024 • Xianming Li, Zongxi Li, Jing Li, Haoran Xie, Qing Li
The experimental results demonstrate the effectiveness of our proposed model in dynamically supporting different embedding sizes and Transformer layers, allowing it to be highly adaptable to various scenarios.
1 code implementation • 21 Feb 2024 • Jiahao Zhang, Rui Xue, Wenqi Fan, Xin Xu, Qing Li, Jian Pei, Xiaorui Liu
In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy.
1 code implementation • 12 Feb 2024 • Haozhen Zhang, Xi Xiao, Le Yu, Qing Li, Zhen Ling, Ye Zhang
In particular, we utilize supervised contrastive learning to enhance the packet-level and flow-level representations and perform graph data augmentation on the byte-level traffic graph so that the fine-grained semantic-invariant characteristics between bytes can be captured through contrastive learning.
1 code implementation • 7 Feb 2024 • Guibiao Liao, Kaichen Zhou, Zhenyu Bao, Kanglin Liu, Qing Li
Second, from the cross-view perspective, we propose a Cross-view Self-enhancement (CSE) strategy to address the challenge raised by view-inconsistent semantics.
no code implementations • 6 Feb 2024 • Qing Li, Zhihang Hu, YiXuan Wang, Lei LI, Yimin Fan, Irwin King, Le Song, Yu Li
Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.
1 code implementation • 3 Feb 2024 • Yi Xin, Jianjiang Yang, Siqi Luo, Haodi Zhou, Junlong Du, Xiaohong Liu, Yue Fan, Qing Li, Yuntao Du
Large-scale pre-trained vision models (PVMs) have shown great potential for adaptability across various downstream vision tasks.
1 code implementation • 31 Jan 2024 • Xu Hu, Yuxi Wang, Lue Fan, Chuanchen Luo, Junsong Fan, Zhen Lei, Qing Li, Junran Peng, Zhaoxiang Zhang
3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed.
1 code implementation • 30 Jan 2024 • Lianbo Ma, Yuee Zhou, Jianlun Ma, Guo Yu, Qing Li
During the gradient descent learning, a one-step forward search is designed to find the trial gradient of the next-step, which is adopted to adjust the gradient of current step towards the direction of fast convergence.
1 code implementation • 26 Jan 2024 • Zhenyu Bao, Guibiao Liao, Zhongyuan Zhao, Kanglin Liu, Qing Li, Guoping Qiu
One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field.
1 code implementation • 23 Jan 2024 • Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu
In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering.
no code implementations • 17 Jan 2024 • Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang, Xuesong Niu, Tengyu Liu, Qing Li, Siyuan Huang
In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data.
no code implementations • 15 Jan 2024 • Qing Li, Lei LI, Yu Li
Central to our focus is the utilizing of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements.
no code implementations • 14 Jan 2024 • Fan Zhang, Shuyi Mao, Qing Li, Xiaojiang Peng
Comparative evaluations with popular point-based methods on HPoint103 and the public dataset DHP19 demonstrate the dramatic outperformance of our D-CPT.
1 code implementation • 13 Jan 2024 • Zhengxin Zhang, Dan Zhao, Xupeng Miao, Gabriele Oliaro, Qing Li, Yong Jiang, Zhihao Jia
Experiments show that QST can reduce the total memory footprint by up to 2. 3 $\times$ and speed up the finetuning process by up to 3 $\times$ while achieving competent performance compared with the state-of-the-art.
1 code implementation • CVPR 2024 • Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao
Additionally a fast version of our method allows for capturing an input image in roughly 26 seconds while surpassing the baseline methods in terms of both reconstruction and editability.
1 code implementation • 26 Dec 2023 • Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao
Additionally, a fast version of our method allows for capturing an input image in roughly 26 seconds, while surpassing the baseline methods in terms of both reconstruction and editability.
no code implementations • CVPR 2024 • Zhi Gao, Yuntao Du, Xintong Zhang, Xiaojian Ma, Wenjuan Han, Song-Chun Zhu, Qing Li
However, these methods often overlook the potential for continual learning, typically by freezing the utilized tools, thus limiting their adaptation to environments requiring new knowledge.
1 code implementation • 13 Dec 2023 • Xulu Zhang, Xiao-Yong Wei, Jinlin Wu, Tianyi Zhang, Zhaoxiang Zhang, Zhen Lei, Qing Li
It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space.
no code implementations • 28 Nov 2023 • Xinhong Chen, Zongxi Li, YaoWei Wang, Haoran Xie, JianPing Wang, Qing Li
To highlight the context in such special causal relationships, we propose a new task to determine whether or not an input pair of emotion and cause has a valid causal relationship under different contexts and extract the specific context clauses that participate in the causal relationship.
no code implementations • 25 Nov 2023 • Simi Job, Xiaohui Tao, Taotao Cai, Haoran Xie, Lin Li, Jianming Yong, Qing Li
In machine learning, exploring data correlations to predict outcomes is a fundamental task.
1 code implementation • 18 Nov 2023 • Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, Siyuan Huang
However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e. g., 3D grounding, embodied reasoning and acting.
no code implementations • 13 Nov 2023 • Shijie Wang, Wenqi Fan, Xiao-Yong Wei, Xiaowei Mei, Shanru Lin, Qing Li
To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance.
1 code implementation • NeurIPS 2023 • Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han
Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.
1 code implementation • 28 Oct 2023 • Xiangyu Zhao, Maolin Wang, Xinjian Zhao, Jiansheng Li, Shucheng Zhou, Dawei Yin, Qing Li, Jiliang Tang, Ruocheng Guo
This survey covers embedding methods like collaborative filtering, self-supervised learning, and graph-based techniques.
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.
1 code implementation • 16 Oct 2023 • Rujie Wu, Xiaojian Ma, Zhenliang Zhang, Wei Wang, Qing Li, Song-Chun Zhu, Yizhou Wang
We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems.
Ranked #3 on
Visual Reasoning
on Bongard-OpenWorld
no code implementations • 15 Oct 2023 • Jiahao Wu, Qijiong Liu, Hengchang Hu, Wenqi Fan, Shengcai Liu, Qing Li, Xiao-Ming Wu, Ke Tang
Notably, the condensation paradigm of this method is forward and free from iterative optimization on the synthesized dataset.
no code implementations • 12 Oct 2023 • Haiyang Liu, Chunjiang Zhu, Detian Zhang, Qing Li
Traffic flow prediction is one of the most fundamental tasks of intelligent transportation systems.
2 code implementations • 2 Oct 2023 • Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie, Jing Li, Fu-lee Wang, Qing Li, Xiaoqin Zhong
We evaluate this approach with Label Supervised LLaMA (LS-LLaMA), based on LLaMA-2-7B, a relatively small-scale LLM, and can be finetuned on a single GeForce RTX4090 GPU.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL03
(F1 (micro) metric)
1 code implementation • 2 Oct 2023 • Jiahao Wu, Wenqi Fan, Jingfan Chen, Shengcai Liu, Qijiong Liu, Rui He, Qing Li, Ke Tang
Specifically, we model the discrete user-item interactions via a probabilistic approach and design a pre-augmentation module to incorporate the potential preferences of users into the condensed datasets.
no code implementations • 22 Sep 2023 • Jiahao Wu, Wenqi Fan, Shengcai Liu, Qijiong Liu, Qing Li, Ke Tang
To model the compatibility between user intents and item properties, we design the user-item co-clustering module, maximizing the mutual information of co-clusters of users and items.
no code implementations • 19 Sep 2023 • Thanveer Shaik, Xiaohui Tao, Lin Li, Haoran Xie, Taotao Cai, Xiaofeng Zhu, Qing Li
These issues compromise both the accuracy and the computational efficiency of models in both Machine Learning and Unlearning.
1 code implementation • 17 Sep 2023 • Qing Li, Huifang Feng, Kanle Shi, Yi Fang, Yu-Shen Liu, Zhizhong Han
We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.
1 code implementation • 4 Sep 2023 • Zhihao Ding, Jieming Shi, Qing Li, Jiannong Cao
For example, on a Bitcoin dataset with 20 million nodes and 203 million edges, DIAM attains an F1 score of 96. 55%, markedly surpassing the runner-up's score of 83. 92%.
no code implementations • 4 Sep 2023 • Runze Gan, Qing Li, Simon Godsill
The non-homogeneous Poisson process (NHPP) is a widely used measurement model that allows for an object to generate multiple measurements over time.
no code implementations • 2 Sep 2023 • Qing Li, Runze Gan, Simon Godsill
Then, we develop a distributed version leveraging the average consensus algorithm, which is theoretically equivalent to the centralised sensor fusion tracker and requires only local message passing with neighbouring sensors.
no code implementations • 9 Aug 2023 • Kaize Shi, Xueyao Sun, Dingxian Wang, Yinlin Fu, Guandong Xu, Qing Li
E-commerce authoring entails creating engaging, diverse, and targeted content to enhance preference elicitation and retrieval experience.
1 code implementation • ICCV 2023 • Ziyu Zhu, Xiaojian Ma, Yixin Chen, Zhidong Deng, Siyuan Huang, Qing Li
3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence.
Ranked #7 on
3D Question Answering (3D-QA)
on SQA3D
no code implementations • 2 Aug 2023 • Jingfan Chen, Yuxi Wang, Pengfei Wang, Xiao Chen, Zhaoxiang Zhang, Zhen Lei, Qing Li
The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes.
1 code implementation • 31 Jul 2023 • Haozhen Zhang, Le Yu, Xi Xiao, Qing Li, Francesco Mercaldo, Xiapu Luo, Qixu Liu
Encrypted traffic classification is receiving widespread attention from researchers and industrial companies.
1 code implementation • 14 Jul 2023 • Zhen Zhang, Guanhua Zhang, Bairu Hou, Wenqi Fan, Qing Li, Sijia Liu, Yang Zhang, Shiyu Chang
This largely falls into the study of certified robust LLMs, i. e., all predictions of LLM are certified to be correct in a local region around the input.
no code implementations • 10 Jul 2023 • Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
The counterfactual explanations help to provide rational and proximate explanations for model fairness, while the attentive action pruning narrows the search space of attributes.
no code implementations • 5 Jul 2023 • Zihuai Zhao, Wenqi Fan, 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.
no code implementations • 3 Jul 2023 • Haixing Dai, Mengxuan Hu, Qing Li, Lu Zhang, Lin Zhao, Dajiang Zhu, Ibai Diez, Jorge Sepulcre, Fan Zhang, Xingyu Gao, Manhua Liu, Quanzheng Li, Sheng Li, Tianming Liu, Xiang Li
Alzheimer's disease (AD) is a neurodegenerative disorder that is beginning with amyloidosis, followed by neuronal loss and deterioration in structure, function, and cognition.
2 code implementations • 2 Jul 2023 • Xunlian Luo, Chunjiang Zhu, Detian Zhang, Qing Li
However, a survey study of graph learning, spatial-temporal graph models for traffic, as well as a fair comparison of baseline models are pending and unavoidable issues.
no code implementations • 24 Jun 2023 • Yang Li, Shihan Ma, Jiamin Zhao, Qing Li, Xinjun Sheng
FSS reduced the sampling of long tracts (10% reduction in fiber length, P<0. 05), and the architectural parameters were within physiological ranges (two parameters with P<0. 05).
1 code implementation • 12 Jun 2023 • Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li
Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention.
1 code implementation • 11 Jun 2023 • Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, Qing Li
In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning.
Ranked #5 on
Text-based de novo Molecule Generation
on ChEBI-20
no code implementations • 30 May 2023 • Chenyi Liu, Vaneet Aggarwal, Tian Lan, Nan Geng, Yuan Yang, Mingwei Xu, Qing Li
By providing a neural network function approximation of this common kernel using graph attention networks, we develop a unified learning-based framework, FERN, for scalable Failure Evaluation and Robust Network design.
no code implementations • 20 May 2023 • Yao Du, Qing Li, Huawei Fan, Meng Zhan, Jinghua Xiao, Xingang Wang
Power systems dominated by renewable energy encounter frequently large, random disturbances, and a critical challenge faced in power-system management is how to anticipate accurately whether the perturbed systems will return to the functional state after the transient or collapse.
1 code implementation • CVPR 2023 • Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han
In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.
no code implementations • 10 May 2023 • Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Xiaofeng Zhu, Qing Li
Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models.
no code implementations • 6 May 2023 • Da Ren, Yi Cai, Qing Li
Generative Adversarial Networks (GANs) have been studied in text generation to tackle the exposure bias problem.
no code implementations • 5 May 2023 • Zongxiong Chen, Jiahui Geng, Derui Zhu, Herbert Woisetschlaeger, Qing Li, Sonja Schimmler, Ruben Mayer, Chunming Rong
The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset.
no code implementations • 30 Apr 2023 • Shaodong Wang, Qing Li, Wenli Zhang
Representing medical concepts for healthcare analytical tasks requires incorporating medical domain knowledge and prior information from patient description data.
no code implementations • 25 Feb 2023 • Haiyang Liu, Chunjiang Zhu, Detian Zhang, Qing Li
The key challenge is to effectively model complex spatial-temporal dependencies and correlations in modern traffic data.
1 code implementation • 24 Feb 2023 • Xunlian Luo, Chunjiang Zhu, Detian Zhang, Qing Li
Accurate and real-time traffic state prediction is of great practical importance for urban traffic control and web mapping services.
no code implementations • 16 Feb 2023 • Xiao Chen, Wenqi Fan, Jingfan Chen, Haochen Liu, Zitao Liu, Zhaoxiang Zhang, Qing Li
Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i. e., clicked by a user) and negative items (i. e., obtained by negative sampling).