3.3k citations · 5.6k across the 26 of their papers we have counts for
26 papers
CAME: Contrastive Automated Model Evaluation
Ru Peng, Qiuyang Duan, Haobo Wang +5
The Automated Model Evaluation (AutoEval) framework entertains the possibility of evaluating a trained machine learning model without resorting to a labeled testing set. Despite th…
TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
Liangyu Zha, Junlin Zhou, Liyao Li +22
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate. The advancements in large language models (LLMs) have made…
Towards Cross-Table Masked Pretraining for Web Data Mining
Chao Ye, Guoshan Lu, Haobo Wang +4
Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information. Given the recent influence of…
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Chenxu Hu, Jie Fu, Chenzhuang Du +3
Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by…
Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning
Hao Chen, Yiming Zhang, Qi Zhang +5
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. While instru…
Latent Processes Identification From Multi-View Time Series
Zenan Huang, Haobo Wang, Junbo Zhao +1
Understanding the dynamics of time series data typically requires identifying the unique latent factors for data generation, \textit{a.k.a.}, latent processes identification. Drive…
Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility
Wentao Ye, Mingfeng Ou, Tianyi Li +8
The recent popularity of large language models (LLMs) has brought a significant impact to boundless fields, particularly through their open-ended ecosystem such as the APIs, open-s…
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
Shuai Zhao, Jinming Wen, Luu Anh Tuan +2
The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot…
Better Sign Language Translation with Monolingual Data
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 relie…
Controllable Textual Inversion for Personalized Text-to-Image Generation
Jianan Yang, Haobo Wang, Yanming Zhang +4
The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts. Text inversion (TI), alongsid…
Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation
Ru Peng, Yawen Zeng, Junbo Zhao
Past works on multimodal machine translation (MMT) elevate bilingual setup by incorporating additional aligned vision information. However, an image-must requirement of the multimo…
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Haobo Wang, Mingxuan Xia, Yixuan Li +4
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 grou…
ProMix: Combating Label Noise via Maximizing Clean Sample Utility
Ruixuan Xiao, Yiwen Dong, Haobo Wang +4
Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific s…
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
Yiming Zhang, Min Zhang, Sai Wu +1
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. The develop…
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Haobo Wang, Ruixuan Xiao, Yixuan Li +4
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 s…
Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network
Ru Peng, Nankai Lin, Yi Fang +4
Syntax knowledge contributes its powerful strength in Neural machine translation (NMT) tasks. Early NMT works supposed that syntax details can be automatically learned from numerou…
Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach
Xuefei Ning, Junbo Zhao, Wenshuo Li +4
Convolutional neural networks (CNNs) are vulnerable to adversarial examples, and studies show that increasing the model capacity of an architecture topology (e.g., width expansion)…
PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
Ziyu Wang, Yiyi Zhang, Yixiao Zhang +4
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE). However, most, if not all, viable attempts on thi…
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
Minjie Wang, Da Zheng, Zihao Ye +12
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and im…
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
Zhilin Yang, Jake Zhao, Bhuwan Dhingra +4
Modern deep transfer learning approaches have mainly focused on learning generic feature vectors from one task that are transferable to other tasks, such as word embeddings in lang…
Prediction Under Uncertainty with Error-Encoding Networks
Mikael Henaff, Junbo Zhao, Yann LeCun
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling components of the future…
Adversarially Regularized Autoencoders
Jake Zhao, Yoon Kim, Kelly Zhang +2
Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures…
Disentangling factors of variation in deep representations using adversarial training
Michael Mathieu, Junbo Zhao, Pablo Sprechmann +2
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary c…
Energy-based Generative Adversarial Network
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 th…