no code implementations • 7 Mar 2025 • Junbo Zhao, Ting Zhang, Jiayu Sun, Mi Tian, Hua Huang
Geometry problem solving has garnered increasing attention due to its potential applications in intelligent education field.
no code implementations • 26 Feb 2025 • Ru Peng, Kexin Yang, Yawen Zeng, Junyang Lin, Dayiheng Liu, Junbo Zhao
In this paper, we train a Data Manager (DataMan) to learn quality ratings and domain recognition from pointwise rating, and use it to annotate a 447B token pre-training corpus with 14 quality ratings and domain type.
no code implementations • 22 Feb 2025 • Shenzhi Yang, Junbo Zhao, Shouqing Yang, Yixuan Li, Dingyu Yang, Xiaofang Zhang, Haobo Wang
Detecting out-of-distribution (OOD) nodes in the graph-based machine-learning field is challenging, particularly when in-distribution (ID) node multi-category labels are unavailable.
no code implementations • 19 Feb 2025 • Qi Zhang, Zhiqing Xiao, Ruixuan Xiao, Lirong Gao, Junbo Zhao
In-context learning (ICL) has demonstrated significant potential in enhancing the capabilities of large language models (LLMs) during inference.
no code implementations • 23 Jan 2025 • Rui Wang, Mingxuan Xia, Chang Yao, Lei Feng, Junbo Zhao, Gang Chen, Haobo Wang
Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i. e., label ambiguity and catastrophic forgetting.
no code implementations • 31 Dec 2024 • Yi Zhang, Mohamadamin Rajabinezhad, Yichao Wang, Junbo Zhao, Shan Zuo
This paper introduces a novel, fully distributed control framework for DC microgrids, enhancing resilience against exponentially unbounded false data injection (EU-FDI) attacks.
no code implementations • 24 Dec 2024 • Mingming Zhang, Zhiqing Xiao, Guoshan Lu, Sai Wu, Weiqiang Wang, Xing Fu, Can Yi, Junbo Zhao
Tabular data, which accounts for over 80% of enterprise data assets, is vital in various fields.
no code implementations • 11 Dec 2024 • Tong Su, Jiangkai Peng, Alaa Selim, Junbo Zhao, Jin Tan
The emergence of grid-forming (GFM) inverter technology and the increasing role of machine learning in power systems highlight the need for evaluating the latest dynamic simulators.
no code implementations • 3 Dec 2024 • Mingming Zhang, Jiahao Hu, Pengfei Shi, Ningtao Wang, Ruizhe Gao, Guandong Sun, Feng Zhao, Yulin kang, Xing Fu, Weiqiang Wang, Junbo Zhao
However, financial datasets in the industry often encounter some challenges, such as data heterogeneity, the predominance of numerical features and the large scale of the data, which can range from tens of millions to hundreds of millions of records.
no code implementations • 24 Nov 2024 • Ziyu Chen, Zhiqing Xiao, Xinbei Jiang, Junbo Zhao
Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents.
no code implementations • 13 Nov 2024 • Tong Su, Junbo Zhao
Existing machine learning-based surrogate modeling methods for transient stability constrained-optimal power flow (TSC-OPF) lack certifications in the presence of unseen disturbances or uncertainties.
1 code implementation • 4 Nov 2024 • Aofeng Su, Aowen Wang, Chao Ye, Chen Zhou, Ga Zhang, Gang Chen, Guangcheng Zhu, Haobo Wang, Haokai Xu, Hao Chen, Haoze Li, Haoxuan Lan, Jiaming Tian, Jing Yuan, Junbo Zhao, Junlin Zhou, Kaizhe Shou, Liangyu Zha, Lin Long, Liyao Li, Pengzuo Wu, Qi Zhang, Qingyi Huang, Saisai Yang, Tao Zhang, Wentao Ye, Wufang Zhu, Xiaomeng Hu, Xijun Gu, Xinjie Sun, Xiang Li, Yuhang Yang, Zhiqing Xiao
In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593. 8K tables and 2. 36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research.
no code implementations • 23 Oct 2024 • Yongqiang Huang, Wentao Ye, Liyao Li, Junbo Zhao
To enhance the comprehension of geometric and spatial relationships in the complex physical world, the study introduces a set of geometric conventions and develops a workflow based on multi-layer graphs and multi-agent system frameworks.
1 code implementation • 17 Oct 2024 • Siwei Wu, Zhongyuan Peng, Xinrun Du, Tuney Zheng, Minghao Liu, Jialong Wu, Jiachen Ma, Yizhi Li, Jian Yang, Wangchunshu Zhou, Qunshu Lin, Junbo Zhao, Zhaoxiang Zhang, Wenhao Huang, Ge Zhang, Chenghua Lin, J. H. Liu
In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i. e., math, coding, commonsense reasoning).
no code implementations • 1 Aug 2024 • Bendong Tan, Jiangkai Peng, Ningchao Gao, Junbo Zhao, Jin Tan
With the increasing integration of inverter-based resources into the power grid, there has been a notable reduction in system inertia, potentially compromising frequency stability.
no code implementations • 29 Jun 2024 • Tong Su, Tong Wu, Junbo Zhao, Anna Scaglione, Le Xie
Due to the availability of more comprehensive measurement data in modern power systems, there has been significant interest in developing and applying reinforcement learning (RL) methods for operation and control.
no code implementations • 21 Jun 2024 • Ruixuan Xiao, Wentao Ma, Ke Wang, Yuchuan Wu, Junbo Zhao, Haobo Wang, Fei Huang, Yongbin Li
Motivated by this, we formalize different formats of workflow knowledge and present FlowBench, the first benchmark for workflow-guided planning.
no code implementations • 14 Jun 2024 • Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, Haobo Wang
Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem.
no code implementations • 31 May 2024 • Lirong Gao, Ru Peng, Yiming Zhang, Junbo Zhao
Prompt recovery in large language models (LLMs) is crucial for understanding how LLMs work and addressing concerns regarding privacy, copyright, etc.
1 code implementation • 20 May 2024 • Wentao Ye, Jiaqi Hu, Liyao Li, Haobo Wang, Gang Chen, Junbo Zhao
The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size.
no code implementations • 2 Apr 2024 • Jiachen Ma, Anda Cao, Zhiqing Xiao, Yijiang Li, Jie Zhang, Chao Ye, Junbo Zhao
In this work, we investigate a more practical and universal attack that does not require the presence of a target model and demonstrate that the high-dimensional text embedding space inherently contains NSFW concepts that can be exploited to generate harmful images.
no code implementations • 11 Mar 2024 • Jiameng Bai, Sai Wu, Jie Song, Junbo Zhao, Gang Chen
As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task.
no code implementations • 27 Feb 2024 • Qi Zhang, Yiming Zhang, Haobo Wang, Junbo Zhao
When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected with a higher probability than other samples.
1 code implementation • 24 Feb 2024 • Alaa Selim, Yanzhu Ye, Junbo Zhao, Bo Yang
To address this challenge, our research presents a novel framework that harnesses the potential of Deep Reinforcement Learning (DRL), specifically utilizing the Importance Weighted Actor-Learner Architecture (IMPALA) algorithm, executed on the RAY platform.
1 code implementation • 23 Jan 2024 • Ru Peng, Heming Zou, Haobo Wang, Yawen Zeng, Zenan Huang, Junbo Zhao
The core of the MDE is to establish a meta-distribution statistic, on the information (energy) associated with individual samples, then offer a smoother representation enabled by energy-based learning.
no code implementations • 12 Jan 2024 • Zeqing Yuan, Haoxuan Lan, Qiang Zou, Junbo Zhao
Recent advancements in implicit 3D representations and generative models have markedly propelled the field of 3D object generation forward.
1 code implementation • CVPR 2024 • Ruixuan Xiao, Lei Feng, Kai Tang, Junbo Zhao, Yixuan Li, Gang Chen, Haobo Wang
Open-world Semi-Supervised Learning aims to classify unlabeled samples utilizing information from labeled data while unlabeled samples are not only from the labeled known categories but also from novel categories previously unseen.
1 code implementation • CVPR 2024 • Lin Long, Haobo Wang, Zhijie Jiang, Lei Feng, Chang Yao, Gang Chen, Junbo Zhao
To cope with this problem we propose a novel PU learning framework namely Latent Group-Aware Meta Disambiguation (LaGAM) which incorporates a hierarchical contrastive learning module to extract the underlying grouping semantics within PU data and produce compact representations.
no code implementations • 10 Dec 2023 • Alaa Selim, Junbo Zhao
This paper introduces a cyber-physical testbed that integrates the Real-Time Digital Simulator (RTDS) with the Real-Time Automation Controller (RTAC) to enhance cybersecurity in electrical distribution networks.
1 code implementation • 27 Nov 2023 • Ruixuan Xiao, Yiwen Dong, Junbo Zhao, Runze Wu, Minmin Lin, Gang Chen, Haobo Wang
While copious solutions, such as active learning for small language models (SLMs) and prevalent in-context learning in the era of large language models (LLMs), have been proposed and alleviate the labeling burden to some extent, their performances are still subject to human intervention.
no code implementations • 21 Nov 2023 • Somayeh Yarahmadi, Daniel Adrian Maldonado, Lamine Mili, Junbo Zhao, Mihai Anitescu
Analyzing these characteristics enables the assessment of the impacts of EMW on the performance of the protection system.
no code implementations • 2 Nov 2023 • Peng Fu, Yiming Zhang, Haobo Wang, Weikang Qiu, Junbo Zhao
Briefly, the core of this technique is rooted in an ideological emphasis on the pruning and purification of the external knowledge base to be injected into LLMs.
no code implementations • 20 Oct 2023 • Ying Zhang, Junbo Zhao, Di Shi, Sungjoo Chung
Distribution system state estimation (DSSE) is paramount for effective state monitoring and control.
no code implementations • 4 Oct 2023 • Hao Chen, Qi Zhang, Zenan Huang, Haobo Wang, Junbo Zhao
Distributional shift between domains poses great challenges to modern machine learning algorithms.
no code implementations • 29 Sep 2023 • Yi Zhang, Yichao Wang, Junbo Zhao, Shan Zuo
In this letter, we study an unified resilient asymmetric bipartite consensus (URABC) problem for nonlinear multi-agent systems with both cooperative and antagonistic interactions under denial-of-service (DoS) attacks.
1 code implementation • ICCV 2023 • Ru Peng, Qiuyang Duan, Haobo Wang, Jiachen Ma, Yanbo Jiang, Yongjun Tu, Xiu Jiang, Junbo Zhao
In this work, we propose Contrastive Automatic Model Evaluation (CAME), a novel AutoEval framework that is rid of involving training set in the loop.
no code implementations • 17 Jul 2023 • Liangyu Zha, Junlin Zhou, Liyao Li, Rui Wang, Qingyi Huang, Saisai Yang, Jing Yuan, Changbao Su, Xiang Li, Aofeng Su, Tao Zhang, Chen Zhou, Kaizhe Shou, Miao Wang, Wufang Zhu, Guoshan Lu, Chao Ye, Yali Ye, Wentao Ye, Yiming Zhang, Xinglong Deng, Jie Xu, Haobo Wang, Gang Chen, Junbo Zhao
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate.
2 code implementations • 10 Jul 2023 • Chao Ye, Guoshan Lu, Haobo Wang, Liyao Li, Sai Wu, Gang Chen, Junbo Zhao
Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information.
no code implementations • 6 Jun 2023 • Chenxu Hu, Jie Fu, Chenzhuang Du, Simian Luo, Junbo Zhao, Hang Zhao
Large language models (LLMs) with memory are computationally universal.
no code implementations • 16 May 2023 • Hao Chen, Yiming Zhang, Qi Zhang, Hantao Yang, Xiaomeng Hu, Xuetao Ma, Yifan Yanggong, Junbo Zhao
Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions.
1 code implementation • 15 May 2023 • Wentao Ye, Mingfeng Ou, Tianyi Li, Yipeng chen, Xuetao Ma, Yifan Yanggong, Sai Wu, Jie Fu, Gang Chen, Haobo Wang, Junbo Zhao
With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses.
1 code implementation • 14 May 2023 • Zenan Huang, Haobo Wang, Junbo Zhao, Nenggan Zheng
Understanding the dynamics of time series data typically requires identifying the unique latent factors for data generation, \textit{a. k. a.
no code implementations • 2 May 2023 • Shuai Zhao, Jinming Wen, Luu Anh Tuan, Junbo Zhao, Jie Fu
Our method does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack.
1 code implementation • 21 Apr 2023 • Ru Peng, Yawen Zeng, Junbo Zhao
Sign language translation (SLT) systems, which are often decomposed into video-to-gloss (V2G) recognition and gloss-to-text (G2T) translation through the pivot gloss, heavily relies on the availability of large-scale parallel G2T pairs.
1 code implementation • 11 Apr 2023 • Jianan Yang, Haobo Wang, YanMing Zhang, Ruixuan Xiao, Sai Wu, Gang Chen, Junbo Zhao
The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts.
1 code implementation • 2 Feb 2023 • Junbo Zhao, Xuefei Ning, Enshu Liu, Binxin Ru, Zixuan Zhou, Tianchen Zhao, Chen Chen, Jiajin Zhang, Qingmin Liao, Yu Wang
In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts.
no code implementations • Conference 2023 • Liyao Li, Haobo Wang, Liangyu Zha, Qingyi Huang, Sai Wu, Gang Chen, Junbo Zhao
Further, we posit that the crucial merit of FETCH is its transferability where the yielded policy network trained on a variety of datasets is indeed capable to enact feature engineering on unseen data, without requiring additional exploration.
1 code implementation • ICCV 2023 • Zenan Huang, Haobo Wang, Junbo Zhao, Nenggan Zheng
In this work, we first characterize that this failure of conventional ML models in DG is attributed to an inadequate identification of causal structures.
1 code implementation • 10 Oct 2022 • Ru Peng, Yawen Zeng, Junbo Zhao
Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme.
Ranked #2 on
Multimodal Machine Translation
on Multi30K
1 code implementation • 21 Sep 2022 • Haobo Wang, Mingxuan Xia, Yixuan Li, YUREN MAO, Lei Feng, Gang Chen, Junbo Zhao
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.
no code implementations • IEEE Transactions on Smart Grid 2022 • Di Cao, Member, Junbo Zhao, Weihao Hu, Senior Member, Qishu Liao, Qi Huang, Zhe Chen, Fellow, IEEE
Abstract—This paper addresses the distribution system state estimation (DSSE) with unknown topology change.
1 code implementation • 21 Jul 2022 • Ruixuan Xiao, Yiwen Dong, Haobo Wang, Lei Feng, Runze Wu, Gang Chen, Junbo Zhao
To overcome the potential side effect of excessive clean set selection procedure, we further devise a novel SSL framework that is able to train balanced and unbiased classifiers on the separated clean and noisy samples.
Ranked #1 on
Learning with noisy labels
on CIFAR-10N-Worst
1 code implementation • Findings (ACL) 2022 • Yiming Zhang, Min Zhang, Sai Wu, Junbo Zhao
The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence.
Ranked #6 on
Aspect-Based Sentiment Analysis (ABSA)
on SemEval-2014 Task-4
(using extra training data)
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
1 code implementation • 22 Jan 2022 • Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
no code implementations • 20 Dec 2021 • Yitong Liu, Zhengshuo Li, Junbo Zhao
To limit the probability of unacceptable worst-case linearization errors that might yield risks for power system operations, this letter proposes a robust data-driven linear power flow (RD-LPF) model.
no code implementations • 23 Nov 2021 • Ru Peng, Nankai Lin, Yi Fang, Shengyi Jiang, Tianyong Hao, BoYu Chen, Junbo Zhao
However, succeeding researches pointed out that limited by the uncontrolled nature of attention computation, the NMT model requires an external syntax to capture the deep syntactic awareness.
1 code implementation • ICLR 2022 • Haobo Wang, Ruixuan Xiao, Sharon Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
no code implementations • 27 May 2021 • Yu Chen, Yuxuan Wang, Bolin Lai, Zijie Chen, Xu Cao, Nanyang Ye, Zhongyuan Ren, Junbo Zhao, Xiao-Yun Zhou, Peng Qi
In the modern medical care, venipuncture is an indispensable procedure for both diagnosis and treatment.
no code implementations • 27 May 2021 • Xu Cao, Zijie Chen, Bolin Lai, Yuxuan Wang, Yu Chen, Zhengqing Cao, Zhilin Yang, Nanyang Ye, Junbo Zhao, Xiao-Yun Zhou, Peng Qi
For the automation, we focus on the positioning part and propose a Dual-In-Dual-Out network based on two-step learning and two-task learning, which can achieve fully automatic regression of the suitable puncture area and angle from near-infrared(NIR) images.
no code implementations • 5 Apr 2021 • Marcos Netto, Junbo Zhao, Lamine Mili
Simulations carried out on the IEEE 39-bus test system reveal that our robust extended Kalman filter exhibits good tracking capabilities under Gaussian process and observation noise while suppressing observation outliers, even in position of leverage.
1 code implementation • 22 Dec 2020 • Xuefei Ning, Junbo Zhao, Wenshuo Li, Tianchen Zhao, Yin Zheng, Huazhong Yang, Yu Wang
In this paper, considering scenarios with capacity budget, we aim to discover adversarially robust architecture at targeted capacities.
no code implementations • 2 Nov 2020 • Xingyu Lei, Student Member, Zhifang Yang, Member, Junbo Zhao, Juan Yu, Senior Member, IEEE
Case studies performed on the PJM 5-bus and IEEE 118-bus systems demonstrate that the proposed method is capable of accurately accounting the influence of wind curtailment dispatch in CCO.
Systems and Control Systems and Control
2 code implementations • 17 Aug 2020 • Ziyu Wang, Yiyi Zhang, Yixiao Zhang, Junyan Jiang, Ruihan Yang, Junbo Zhao, Gus Xia
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE).
no code implementations • 24 Jun 2020 • Di Cao, Junbo Zhao, Weihao Hu, Fei Ding, Qi Huang, Zhe Chen, Frede Blaabjerg
Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage controls, but this is difficult to obtain in practice.
no code implementations • 31 May 2020 • Di Cao, Junbo Zhao, Weihao Hu, Fei Ding, Qi Huang, Zhe Chen
This paper proposes a data-driven distributed voltage control approach based on the spectrum clustering and the enhanced multi-agent deep reinforcement learning (MADRL) algorithm.
no code implementations • 31 May 2020 • Xingyu Lei, Zhifang Yang, Juan Yu, Junbo Zhao, Qian Gao, Hongxin Yu
This paper proposes a data-driven approach for optimal power flow (OPF) based on the stacked extreme learning machine (SELM) framework.
BIG-bench Machine Learning
Physics-informed machine learning
no code implementations • 11 May 2020 • Junbo Zhao, Marcos Netto, Zhenyu Huang, Samson Shenglong Yu, Antonio Gomez-Exposito, Shaobu Wang, Innocent Kamwa, Shahrokh Akhlaghi, Lamine Mili, Vladimir Terzija, A. P. Sakis Meliopoulos, Bikash Pal, Abhinav Kumar Singh, Ali Abur, Tianshu Bi, Alireza Rouhani
Power system dynamic state estimation (DSE) remains an active research area.
no code implementations • ICLR 2018 • Mikael Henaff, Junbo Zhao, Yann Lecun
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty.
1 code implementation • 14 Nov 2017 • Mikael Henaff, Junbo Zhao, Yann Lecun
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty.
no code implementations • NeurIPS 2016 • Michael F. Mathieu, Junbo Jake Zhao, Junbo Zhao, Aditya Ramesh, Pablo Sprechmann, Yann Lecun
The only available source of supervision during the training process comes from our ability to distinguish among different observations belonging to the same category.
3 code implementations • 10 Nov 2016 • Michael Mathieu, Junbo Zhao, Pablo Sprechmann, Aditya Ramesh, Yann Lecun
During training, the only available source of supervision comes from our ability to distinguish among different observations belonging to the same class.
3 code implementations • 11 Sep 2016 • Junbo Zhao, Michael Mathieu, Yann Lecun
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions.
30 code implementations • NeurIPS 2015 • Xiang Zhang, Junbo Zhao, Yann Lecun
This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification.
Ranked #16 on
Sentiment Analysis
on Yelp Fine-grained classification
2 code implementations • 8 Jun 2015 • Junbo Zhao, Michael Mathieu, Ross Goroshin, Yann Lecun
The objective function includes reconstruction terms that induce the hidden states in the Deconvnet to be similar to those of the Convnet.