Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks104 from public data
- 2,152
- 2,024
- ResNeSt: Split-Attention Networks1,789
This work designs a new variant of the ResNet model, named ResNeSt, which outperforms EfficientNet in terms of the accuracy/latency trade-off and applies channel-wise attention across different network branches to leverage the complementary strengths of both feature-map attention and multi-path representation.
- Bag of Tricks for Image Classification with Convolutional Neural Networks1,654
This paper examines a collection of training procedure refinements and empirically evaluates their impact on the final model accuracy through ablation study, and shows that by combining these refinements together, they are able to improve various CNN models significantly.
- 1,021
- Multimodal Chain-of-Thought Reasoning in Language Models966
This work proposes Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework that separates rationale generation and answer inference, and indicates that it offers the advantages of mitigating hallucination and enhancing convergence speed.
- Communication Efficient Distributed Machine Learning with the Parameter Server711
An in-depth analysis of two large scale machine learning problems ranging from l1 -regularized logistic regression on CPUs to reconstruction ICA on GPUs, using 636TB of real data with hundreds of billions of samples and dimensions is presented.
- 521
- 439
- Chinese Word Segmentation and Named Entity Recognition: A Pragmatic Approach231
A pragmatic mathematical framework in which segmenting known words and detecting unknown words of different types can be performed simultaneously in a unified way is proposed and implemented in an adaptive Chinese word segmenter, called MSRSeg, which is described in detail.
- 229
- 201
- An Improved Chinese Word Segmentation System with Conditional Random Field185
It is found that the use of a 6-tag set, tone feature of Chinese character and assistant segmenters trained on other corpora further improve Chinese word segmentation performance.
- 142
- Regularizing Neural Machine Translation by Target-Bidirectional Agreement121
A novel model regularization method is proposed for NMT training, which aims to improve the agreement between translations generated by left-to-right (L2R) and right-to-left (R2L) NMT decoders, and significantly outperforms state-of-the-art baselines on Chinese-English and English-German translation tasks.
- Joint Training for Neural Machine Translation Models with Monolingual Data119
Experimental results on Chinese-English and English-German translation tasks show that the proposed approach can simultaneously improve translation quality of source-to-target and target- to-source models, significantly outperforming strong baseline systems which are enhanced with monolingual data for model training including back-translation.
- Improving Query Spelling Correction Using Web Search Results103
A novel method is proposed for use of web search results to improve the existing query spelling correction models solely based on query logs by leveraging the rich information on the web related to the query and its top-ranked candidate.
- 99
- FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems97
FeatGraph incorporates optimizations for graph traversal into the sparse templates and allows users to specify optimizations for UDFs with a feature dimension schedule (FDS) and FeatGraph speeds up end-to-end GNN training and inference by up to 32$ \times on CPU and 7$\times on GPU.
- 92
- A Unified Character-Based Tagging Framework for Chinese Word Segmentation87
The results show that a simple learning system with six n-gram feature templates and a six-tag set can obtain competitive performance in the cases of learning only from a training corpus and an ensemble learning technique, assistant segmenter, is proposed and its effectiveness is verified.
- Word Alignment Modeling with Context Dependent Deep Neural Network77
A novel bilingual word alignment approach based on DNN (Deep Neural Network) which outperforms the HMM and IBM model 4 baselines by 2 points in F-score and generates a very compact model with much fewer parameters.
- 72
- 71
- Improved source-channel models for Chinese word segmentation69
A Chinese word segmentation system that uses improved source-channel models of Chinese sentence generation and provides a unified approach to the four fundamental features of word-level Chinese language processing.
- MiCS60
MiCS, which Minimizes the Communication Scale to bring down communication overhead is proposed, which can utilize heterogeneous network bandwidth, reduce network traffic over slower links, reduce the latency of communications for maintaining high network bandwidth utilization, and amortize expensive global gradient synchronization overhead.
- DiFacto56
DiFacto is described, which uses a refined Factorization Machine model with sparse memory adaptive constraints and frequency adaptive regularization, and it is shown how to distribute DiFacto over multiple machines using the Parameter Server framework by computing distributed subgradients on minibatches asynchronously.
- Inferring Movement Trajectories from GPS Snippets54
This paper presents a complete and computationally tractable model for estimating and predicting trajectories based on sparsely sampled, anonymous GPS land-marks that they call GPS snippets, and uses mapping data as side information to constrain the inference process.
- Adaptive Chinese word segmentation53
A statistical framework where domain-specific words are identified in a unified approach to word segmentation based on linear models is presented and a transformation-based learning method used to adapt the system to differentword segmentation standards is described.
- BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training52
A new large-scale benchmark termed BigDetection is constructed, which has 600 object categories and contains over 3.4M training images with 36M bounding boxes and a new taxonomy is generated which unifies the heterogeneous label spaces from different sources.
- Learned Image Compression with Dictionary-Based Entropy Model51
A novel entropy model named Dictionary-Based Cross Attention Entropy model is proposed, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model.
- 49
- 44
- A Unified Optimization Approach for CNN Model Inference on Integrated GPUs38
This paper proposes an end-to-end solution to execute CNN model inference on the integrated GPUs at the edge, which uses a unified IR to represent and optimize vision-specific operators on integrated GPUs from multiple vendors, as well as leverages machine learning-based scheduling search schemes to optimize computationally-intensive operators like convolution.
- A Unified Efficient Pyramid Transformer for Semantic Segmentation35
This work proposes a unified framework (UN-EPT) to segment objects by considering both context information and boundary artifacts, and demonstrates promising performance on three popular benchmarks for semantic segmentation with low memory footprint.
- Triangular Architecture for Rare Language Translation35
Empirical results demonstrate that the proposed novel triangular training architecture (TA-NMT) significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.
- Bidirectional Generative Adversarial Networks for Neural Machine Translation34
A novel Bidirectional Generative Adversarial Network for Neural Machine Translation (BGAN-NMT) is proposed, which aims to introduce a generator model to act as the discriminator, whereby the discriminators naturally considers the entire translation space so that the inadequate training problem can be alleviated.
- 30
- 30
- 29
- 28
- 26
- 23
- 23
- 22
- 21
- 17
- 17
- 16
- 15
- 14
- 11
- 11
- 11
- 10
- 10
- 9
- 9
- 8
- 8
- 7
- 7
- Generative Bridging Network for Neural Sequence Prediction7
Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN are proposed to penalize confidence, enhance language smoothness and relieve learning burden, show that they can yield significant improvements over strong baselines.
- 7
- 6
- SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning5
SPT, a semi-parametric prompt tuning method for multitask prompted learning, which is a memory bank from where memory prompts are retrieved based on discrete prompts, is proposed.
- 5
- 5
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- Neural Sequence Prediction by Coaching.2
This paper introduces a hybrid-coach framework to combine these two existing algorithms so that the supervision from MLE can stabilize RL training while RL can incorporate task-level loss into MLE training.
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.