1 code implementation • 16 Apr 2024 • Yiming Zhang, Avi Schwarzschild, Nicholas Carlini, Zico Kolter, Daphne Ippolito
Despite being trained specifically to follow user instructions, today's language models perform poorly when instructed to produce random outputs.
no code implementations • 15 Apr 2024 • Yiming Zhang, Zhuokai Zhao, Zhaorun Chen, Zhili Feng, Zenghui Ding, Yining Sun
Among the ever-evolving development of vision-language models, contrastive language-image pretraining (CLIP) has set new benchmarks in many downstream tasks such as zero-shot classifications by leveraging self-supervised contrastive learning on large amounts of text-image pairs.
no code implementations • 8 Apr 2024 • Tianyu Chen, Yiming Zhang, Guoxin Yu, Dapeng Zhang, Li Zeng, Qing He, Xiang Ao
In this paper, we extend financial sentiment analysis~(FSA) to event-level since events usually serve as the subject of the sentiment in financial text.
no code implementations • 4 Apr 2024 • Yiming Zhang, Zhe Wang, Xinjie Li, Yunchen Yuan, Chengsong Zhang, Xiao Sun, Zhihang Zhong, Jian Wang
Human body restoration plays a vital role in various applications related to the human body.
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.
no code implementations • 20 Feb 2024 • Jiaqi Ma, Vivian Lai, Yiming Zhang, Chacha Chen, Paul Hamilton, Davor Ljubenkov, Himabindu Lakkaraju, Chenhao Tan
However, properly evaluating the effectiveness of the XAI methods inevitably requires the involvement of human subjects, and conducting human-centered benchmarks is challenging in a number of ways: designing and implementing user studies is complex; numerous design choices in the design space of user study lead to problems of reproducibility; and running user studies can be challenging and even daunting for machine learning researchers.
1 code implementation • 21 Dec 2023 • Yiming Zhang, Zhening Xing, Yanhong Zeng, Youqing Fang, Kai Chen
Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation, empowering non-experts to generate stunning images with unique styles.
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 • Yu Ji, Qi Shen, Shixuan Zhu, Hang Yu, Yiming Zhang, Chuan Cui, Zhihua Wei
Therefore, we propose a novel conversational recommendation scenario named Multi-Subsession Multi-round Conversational Recommendation (MSMCR), where user would still resort to CRS after several subsessions and might preserve vague interests, and system would proactively ask attributes to activate user interests in the current subsession.
no code implementations • ICCV 2023 • Yiming Zhang, ZeMing Gong, Angel X. Chang
We introduce the task of localizing a flexible number of objects in real-world 3D scenes using natural language descriptions.
1 code implementation • 31 Aug 2023 • Yiming Zhang, Tianang Leng, Kun Han, Xiaohui Xie
In conclusion, we present a novel approach for rapid online adaptation in interactive image segmentation, adapting to a new organ in just 0. 83 minutes.
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.
no code implementations • 13 Jul 2023 • Yiming Zhang, Nicholas Carlini, Daphne Ippolito
In experiments with 3 different sources of prompts and 11 underlying large language models, we find that simple text-based attacks can in fact reveal prompts with high probability.
no code implementations • 13 Jun 2023 • Yangqiaoyu Zhou, Yiming Zhang, Chenhao Tan
Natural language explanations have the potential to provide rich information that in principle guides model reasoning.
no code implementations • 23 May 2023 • Yiming Zhang, Sravani Nanduri, Liwei Jiang, Tongshuang Wu, Maarten Sap
Toxicity annotators and content moderators often default to mental shortcuts when making decisions.
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.
no code implementations • 23 Jan 2023 • Vivian Lai, Yiming Zhang, Chacha Chen, Q. Vera Liao, Chenhao Tan
As a result, current XAI techniques are often found to be hard to use and lack effectiveness.
1 code implementation • 8 Nov 2022 • Yiming Zhang, Shi Feng, Chenhao Tan
For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5. 8\%$ improvement on average.
no code implementations • 4 Nov 2022 • Jingchang Zhuge, Huiyuan Liang, Yiming Zhang, Shichao Li, Xinyu Yang, Jun Wu
Aircraft taxiing conflict is a threat to the safety of airport operations, mainly due to the human error in control command infor-mation.
no code implementations • 19 Oct 2022 • Shixuan Zhu, Qi Shen, Yiming Zhang, Zhenwei Dong, Zhihua Wei
In this paper, we propose a novel graph learning paradigm called Counterfactual Learning for Bundle Recommendation (CLBR) to mitigate the impact of data sparsity problem and improve bundle recommendation.
1 code implementation • 5 Oct 2022 • Eesha Kumar, Yiming Zhang, Stefano Pini, Simon Stent, Ana Ferreira, Sergey Zagoruyko, Christian S. Perone
The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states.
no code implementations • 23 May 2022 • Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton, Chenhao Tan
Despite the strong performance of current NLP models, they can be brittle against adversarial attacks.
1 code implementation • 18 Apr 2022 • Yiming Zhang, Hong Yu, Ruoyi Du, Zhanyu Ma, Yuan Dong
To eliminate this negative effect, in this paper, we propose a two-stage framework for audio captioning: (i) in the first stage, via the contrastive learning, we construct a proxy feature space to reduce the distances between captions correlated to the same audio, and (ii) in the second stage, the proxy feature space is utilized as additional supervision to encourage the model to be optimized in the direction that benefits all the correlated captions.
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 #4 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
no code implementations • 19 Jan 2022 • Yue Ruan, Han-Hung Lee, Yiming Zhang, Ke Zhang, Angel X. Chang
Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data.
no code implementations • 31 Dec 2021 • Qi Shen, Shixuan Zhu, Yitong Pang, Yiming Zhang, Zhihua Wei
Session-based recommendation (SBR) is a challenging task, which aims at recommending next items based on anonymous interaction sequences.
1 code implementation • 31 Dec 2021 • Chuan Cui, Qi Shen, Shixuan Zhu, Yitong Pang, Yiming Zhang, Hanning Gao, Zhihua Wei
Session-based recommendation (SBR) is proposed to recommend items within short sessions given that user profiles are invisible in various scenarios nowadays, such as e-commerce and short video recommendation.
no code implementations • 27 Dec 2021 • Yiqing Ma, Hao Wang, Yiming Zhang, Kai Chen
ByteScheduler partitions and rearranges tensor transmissions to improve the communication efficiency of distributed Deep Neural Network (DNN) training.
1 code implementation • 22 Dec 2021 • Yiming Zhang, Lingfei Wu, Qi Shen, Yitong Pang, Zhihua Wei, Fangli Xu, Bo Long, Jian Pei
As a result, we first propose a more realistic CRS learning setting, namely Multi-Interest Multi-round Conversational Recommendation, where users may have multiple interests in attribute instance combinations and accept multiple items with partially overlapped combinations of attribute instances.
1 code implementation • NeurIPS 2021 • Yiyue Qian, Yiming Zhang, Yanfang Ye, Chuxu Zhang
In this paper, we propose a holistic framework named MetaHG to automatically detect illicit drug traffickers on social media (i. e., Instagram), by tackling the following two new challenges: (1) different from existing works which merely focus on analyzing post content, MetaHG is capable of jointly modeling multi-modal content and relational structured information on social media for illicit drug trafficker detection; (2) in addition, through the proposed meta-learning technique, MetaHG addresses the issue of requiring sufficient data for model training.
no code implementations • 17 Nov 2021 • Yanqiu Wu, Xinyue Chen, Che Wang, Yiming Zhang, Keith W. Ross
In particular, Truncated Quantile Critics (TQC) achieves state-of-the-art asymptotic training performance on the MuJoCo benchmark with a distributional representation of critics; and Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency that is competitive with state-of-the-art model-based methods using a high update-to-data ratio and target randomization.
no code implementations • 18 Oct 2021 • Shengwei Li, Zhiquan Lai, Dongsheng Li, Yiming Zhang, Xiangyu Ye, Yabo Duan
EmbRace introduces Sparsity-aware Hybrid Communication, which integrates AlltoAll and model parallelism into data-parallel training, so as to reduce the communication overhead of highly sparse parameters.
no code implementations • 24 Sep 2021 • Qi Shen, Lingfei Wu, Yitong Pang, Yiming Zhang, Zhihua Wei, Fangli Xu, Bo Long
Based on the global graph, MGCNet attaches the global interest representation to final item representation based on local contextual intention to address the limitation (iii).
no code implementations • 24 Sep 2021 • Yiming Zhang, Lingfei Wu, Qi Shen, Yitong Pang, Zhihua Wei, Fangli Xu, Ethan Chang, Bo Long
In this work, we propose an end-to-end heterogeneous global graph learning framework, namely Graph Learning Augmented Heterogeneous Graph Neural Network (GL-HGNN) for social recommendation.
no code implementations • 4 Aug 2021 • Wubing B. Qin, Yiming Zhang, Dénes Takács, Gábor Stépán, Gábor Orosz
The models are categorized based on how they represent the wheel-ground contact, whether they incorporate the longitudinal dynamics, and whether they consider the steering dynamics.
1 code implementation • 8 Jul 2021 • Yitong Pang, Lingfei Wu, Qi Shen, Yiming Zhang, Zhihua Wei, Fangli Xu, Ethan Chang, Bo Long, Jian Pei
Additionally, existing personalized session-based recommenders capture user preference only based on the sessions of the current user, but ignore the useful item-transition patterns from other user's historical sessions.
no code implementations • 14 Jun 2021 • Yiming Zhang, Keith W. Ross
Based on this bound, we develop an iterative procedure which produces a sequence of monotonically improved policies for the average reward criterion.
no code implementations • 13 Apr 2021 • Ning Liu, Songlei Jian, Dongsheng Li, Yiming Zhang, Zhiquan Lai, Hongzuo Xu
Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks.
1 code implementation • 12 Mar 2021 • Steven Atkinson, Yiming Zhang, Liping Wang
Remarkably, we find that the physics learned from the first specimen allows us to understand the backscattering observed in the latter sample, a qualitative feature that is wholly absent from the specimen from which the physics were inferred.
1 code implementation • 16 Feb 2021 • Jiajun Bao, Junjie Wu, Yiming Zhang, Eshwar Chandrasekharan, David Jurgens
Online conversations can go in many directions: some turn out poorly due to antisocial behavior, while others turn out positively to the benefit of all.
no code implementations • 4 Feb 2021 • Ke Chen, Xiaojing Bai, Xulin Mu, Pengfei Yan, Nianxiang Qiu, Youbing Li, Jie zhou, Yujie Song, Yiming Zhang, Shiyu Du, Zhifang Chai, Qing Huang
The elemental diversity is crucial to screen out ternary MAX phases with outstanding properties via tuning of bonding types and strength between constitutive atoms.
Materials Science
no code implementations • 1 Jan 2021 • Yiming Zhang, Keith W. Ross
In continuing control tasks, an agent’s average reward per time step is a more natural performance measure compared to the commonly used discounting framework as it can better capture an agent’s long-term behavior.
no code implementations • 14 Aug 2020 • Waad Subber, Sayan Ghosh, Piyush Pandita, Yiming Zhang, Liping Wang
The region of interest can be specified based on the localization features of the solution, user interest, and correlation length of the random material properties.
no code implementations • 21 Jul 2020 • Jiahong Wu, Jianfei Lu, Xinxin Kang, Yiming Zhang, Yinhang Tang, Jianfei Song, Ze Huang, Shenglan Ben, Jiashui Huang, Faen Zhang
Panoramic segmentation is a scene where image segmentation tasks is more difficult.
1 code implementation • CVPR 2020 • Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Yiming Zhang, Kai Xu, Jun Wang
We demonstrate these by capturing contextual information at patch, object and scene levels.
no code implementations • 26 Mar 2020 • Sayan Ghosh, Piyush Pandita, Steven Atkinson, Waad Subber, Yiming Zhang, Natarajan Chennimalai Kumar, Suryarghya Chakrabarti, Liping Wang
The methodology, called GE's Bayesian Hybrid Modeling (GEBHM), is a probabilistic modeling method, based on the Kennedy and O'Hagan framework, that has been continuously scaled-up and industrialized over several years.
2 code implementations • NeurIPS 2020 • Yiming Zhang, Quan Vuong, Keith W. Ross
We propose a novel approach called First Order Constrained Optimization in Policy Space (FOCOPS) which maximizes an agent's overall reward while ensuring the agent satisfies a set of cost constraints.
1 code implementation • WS 2019 • Hongyu Li, Xiyuan Zhang, Yibing Liu, Yiming Zhang, Quan Wang, Xiangyang Zhou, Jing Liu, Hua Wu, Haifeng Wang
In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.
no code implementations • 26 Jul 2019 • Sayan Ghosh, Jesper Kristensen, Yiming Zhang, Waad Subber, Liping Wang
Multi-fidelity Gaussian process is a common approach to address the extensive computationally demanding algorithms such as optimization, calibration and uncertainty quantification.
1 code implementation • ICLR 2019 • Quan Vuong, Yiming Zhang, Keith W. Ross
We show how the Natural Policy Gradient and Trust Region Policy Optimization (NPG/TRPO) problems, and the Proximal Policy Optimization (PPO) problem can be addressed by this methodology.
no code implementations • 1 Jul 2018 • Yujie Fan, Yiming Zhang, Yanfang Y e∗, Xin Li
Opioid (e. g., heroin and morphine) addiction has become one of the largest and deadliest epidemics in the United States.
no code implementations • 2 Jun 2018 • Yiming Zhang, Quan Ho Vuong, Kenny Song, Xiao-Yue Gong, Keith W. Ross
We develop several novel unbiased estimators for the entropy bonus and its gradient.
1 code implementation • ICLR 2019 • Quan Vuong, Yiming Zhang, Keith W. Ross
We show how the Natural Policy Gradient and Trust Region Policy Optimization (NPG/TRPO) problems, and the Proximal Policy Optimization (PPO) problem can be addressed by this methodology.
3 code implementations • 27 Mar 2018 • Zheng Qin, Zhaoning Zhang, Dongsheng Li, Yiming Zhang, Yuxing Peng
Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds.
no code implementations • ICLR 2018 • Vuong Ho Quan, Yiming Zhang, Kenny Song, Xiao-Yue Gong, Keith W. Ross
In the case of high-dimensional action spaces, calculating the entropy and the gradient of the entropy requires enumerating all the actions in the action space and running forward and backpropagation for each action, which may be computationally infeasible.