no code implementations • EMNLP 2021 • Zhenxi Lin, Qianli Ma, Jiangyue Yan, Jieyu Chen
Metaphors are ubiquitous in natural language, and detecting them requires contextual reasoning about whether a semantic incongruence actually exists.
no code implementations • Findings (ACL) 2022 • Junhao Zheng, Haibin Chen, Qianli Ma
Cross-domain NER is a practical yet challenging problem since the data scarcity in the real-world scenario.
no code implementations • EMNLP 2020 • Qianli Ma, Zhenxi Lin, Jiangyue Yan, Zipeng Chen, Liuhong Yu
The central problem of sentence classification is to extract multi-scale n-gram features for understanding the semantic meaning of sentences.
no code implementations • 30 Oct 2023 • Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma
Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation.
no code implementations • 16 Oct 2023 • Qianli Ma, Haotian Zhou, Tingkai Liu, Jianbo Yuan, PengFei Liu, Yang You, Hongxia Yang
Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs).
no code implementations • 16 Oct 2023 • Haotian Zhou, Tingkai Liu, Qianli Ma, Jianbo Yuan, PengFei Liu, Yang You, Hongxia Yang
In this paper, we introduce a new dimension in SFT data selection: learnability.
no code implementations • 22 Sep 2023 • Jian Xu, Shian Du, Junmei Yang, Qianli Ma, Delu Zeng
Furthermore, our method guarantees theoretically controlled prediction error for DGP models and demonstrates remarkable performance on various datasets.
1 code implementation • 19 Jun 2023 • Junhao Zheng, Qianli Ma, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen
Intriguingly, the unified objective can be seen as the sum of the vanilla fine-tuning objective, which learns new knowledge from target data, and the causal objective, which preserves old knowledge from PLMs.
no code implementations • 25 May 2023 • Huawen Feng, Zhenxi Lin, Qianli Ma
In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn.
1 code implementation • 18 May 2023 • Qianli Ma, Zhen Liu, Zhenjing Zheng, Ziyang Huang, Siying Zhu, Zhongzhong Yu, James T. Kwok
Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications.
1 code implementation • ICCV 2023 • Siwei Zhang, Qianli Ma, Yan Zhang, Sadegh Aliakbarian, Darren Cosker, Siyu Tang
One of the biggest challenges of this task is severe body truncation due to close social distances in egocentric scenarios, which brings large pose ambiguities for unseen body parts.
no code implementations • ICCV 2023 • Sergey Prokudin, Qianli Ma, Maxime Raafat, Julien Valentin, Siyu Tang
In this work, we present a dynamic point field model that combines the representational benefits of explicit point-based graphics with implicit deformation networks to allow efficient modeling of non-rigid 3D surfaces.
1 code implementation • 4 Dec 2022 • Junlong Liu, Xichen Shang, Qianli Ma
Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention.
1 code implementation • 8 Oct 2022 • Junhao Zheng, Zhanxian Liang, Haibin Chen, Qianli Ma
Thanks to the causal inference, we identify that the forgetting is caused by the missing causal effect from the old data.
Ranked #1 on
FG-1-PG-1
on conll2003
no code implementations • 14 Sep 2022 • Qianli Ma, Jinlong Yang, Michael J. Black, Siyu Tang
Specifically, we extend point-based methods with a coarse stage, that replaces canonicalization with a learned pose-independent "coarse shape" that can capture the rough surface geometry of clothing like skirts.
1 code implementation • 14 Dec 2021 • Siwei Zhang, Qianli Ma, Yan Zhang, Zhiyin Qian, Taein Kwon, Marc Pollefeys, Federica Bogo, Siyu Tang
Key to reasoning about interactions is to understand the body pose and motion of the interaction partner from the egocentric view.
no code implementations • ICCV 2021 • Qianli Ma, Jinlong Yang, Siyu Tang, Michael J. Black
The geometry feature can be optimized to fit a previously unseen scan of a person in clothing, enabling the scan to be reposed realistically.
no code implementations • ACL 2021 • Xichen Shang, Qianli Ma, Zhenxi Lin, Jiangyue Yan, Zipeng Chen
Sequential sentence classification aims to classify each sentence in the document based on the context in which sentences appear.
1 code implementation • ACL 2021 • Haibin Chen, Qianli Ma, Zhenxi Lin, Jiangyue Yan
We then introduce a joint embedding loss and a matching learning loss to model the matching relationship between the text semantics and the label semantics.
1 code implementation • NeurIPS 2021 • Shaofei Wang, Marko Mihajlovic, Qianli Ma, Andreas Geiger, Siyu Tang
In contrast, we propose an approach that can quickly generate realistic clothed human avatars, represented as controllable neural SDFs, given only monocular depth images.
no code implementations • 17 Jun 2021 • Sen Li, Fuyu Lv, Taiwei Jin, Guli Lin, Keping Yang, Xiaoyi Zeng, Xiao-Ming Wu, Qianli Ma
We evaluate MGDSPR on Taobao Product Search with significant metrics gains observed in offline experiments and online A/B tests.
1 code implementation • AAAI 2021 • Qianli Ma, Chuxin Chen, Sen Li, Garrison W. Cottrell
Also, to reduce the error propagation from imputation to clustering, we introduce a discriminator to make the distribution of imputation values close to the true one and train CRLI in an alternating train- ing manner.
1 code implementation • CVPR 2021 • Qianli Ma, Shunsuke Saito, Jinlong Yang, Siyu Tang, Michael J. Black
We demonstrate the efficacy of our surface representation by learning models of complex clothing from point clouds.
2 code implementations • CVPR 2021 • Shunsuke Saito, Jinlong Yang, Qianli Ma, Michael J. Black
We present SCANimate, an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar.
1 code implementation • 12 Aug 2020 • Siwei Zhang, Yan Zhang, Qianli Ma, Michael J. Black, Siyu Tang
To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world.
2 code implementations • NeurIPS 2019 • Qianli Ma, Jiawei Zheng, Sen Li, Gary W. Cottrell
When applying seq2seq to time series clustering, obtaining a representation that effectively represents the temporal dynamics of the sequence, multi-scale features, and good clustering properties remains a challenge.
1 code implementation • CVPR 2020 • Qianli Ma, Jinlong Yang, Anurag Ranjan, Sergi Pujades, Gerard Pons-Moll, Siyu Tang, Michael J. Black
To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.
1 code implementation • 8 Jul 2019 • Wenguang Yuan, Jia Wei, Jiabing Wang, Qianli Ma, Tolga Tasdizen
Currently, most deep models for multimodal segmentation rely on paired registered images.
1 code implementation • 3 Jun 2019 • Yan Zhang, Krikamol Muandet, Qianli Ma, Heiko Neumann, Siyu Tang
In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form.
no code implementations • 30 Jun 2018 • Min Zhang, Qianli Ma, Chengfeng Wen, Hai Chen, Deruo Liu, Xianfeng GU, Jie He, Xiaoyin Xu
The Wasserstein distance between the nodules is calculated based on our new spherical optimal mass transport, this new algorithm works directly on sphere by using spherical metric, which is much more accurate and efficient than previous methods.
no code implementations • 13 Nov 2017 • Qianli Ma, Lifeng Shen, Garrison W. Cottrell
As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade.
1 code implementation • 9 May 2016 • The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.