Search Results for author:
Found 69 papers, 31 papers with code
Challenges to Open-Domain Constituency Parsing
Neural constituency parsers have reached practical performance on news-domain benchmarks.
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation
Moreover, this task can be used to improve visual question generation and visual question answering.
2L3: Lifting Imperfect Generated 2D Images into Accurate 3D
Specifically, we first leverage to decouple the shading information from the generated images to reduce the impact of inconsistent lighting; then, we introduce mono prior with view-dependent transient encoding to enhance the reconstructed normal; and finally, we design a view augmentation fusion strategy that minimizes pixel-level loss in generated sparse views and semantic loss in augmented random views, resulting in view-consistent geometry and detailed textures.
Multi-Candidate Speculative Decoding
One way to speed them up is speculative decoding, which generates candidate segments (a sequence of tokens) from a fast draft model that is then verified in parallel by the target model.
SeaLLMs -- Large Language Models for Southeast Asia
Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regional languages.
Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs
Though prompting LLMs with various reasoning structures produces reasoning proofs along with answers, these proofs are not ensured to be causal and reliable due to the inherent defects of LLMs.
Once Upon a $\textit{Time}$ in $\textit{Graph}$: Relative-Time Pretraining for Complex Temporal Reasoning
However, the knowledge-time association is usually insufficient for the downstream tasks that require reasoning over temporal dependencies between knowledge.
Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge
The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains.
ADNet: Lane Shape Prediction via Anchor Decomposition
In this paper, we revisit the limitations of anchor-based lane detection methods, which have predominantly focused on fixed anchors that stem from the edges of the image, disregarding their versatility and quality.
SNR-based beaconless multi-scan link acquisition model with vibration for LEO-to-ground laser communication
Specially, under the combined effects of platform vibration and turbulence, we decouple the parameters of beam divergence angle, spiral pitch, and coverage factor at a fixed transmitted power for a given average received SNR threshold.
Enhancing Grammatical Error Correction Systems with Explanations
Grammatical error correction systems improve written communication by detecting and correcting language mistakes.
MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine
The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts.
Why is the winner the best?
The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning.
CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.
Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens
In this paper we present a novel method to estimate 3D human pose and shape from monocular videos.
Ranked #36 on
3D Human Pose Estimation
on 3DPW
Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading
We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19, 461 whole-slide images of prostate cancer from multiple centers.
Artificial intelligence for diagnosing and predicting survival of patients with renal cell carcinoma: Retrospective multi-center study
The OSrisk for the prediction of 5-year survival status achieved AUC of 0. 784 (0. 746-0. 819) in the TCGA cohort, which was further verified in the independent General cohort and the CPTAC cohort, with AUC of 0. 774 (0. 723-0. 820) and 0. 702 (0. 632-0. 765), respectively.
Hyperbolic Cosine Transformer for LiDAR 3D Object Detection
The cosh-attention module reduces the space and time complexity of the attention operation.
DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep Learning
The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field.
Exploring Runtime Decision Support for Trauma Resuscitation
The best model achieved an average F1-score of 0. 67 for 61 activity types.
LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction
When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates.
Nuclear Norm Maximization Based Curiosity-Driven Learning
To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states.
Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types
MC-TMB algorithm also exhibited good generalization on the external validation cohort with an AUC of 0. 732 (0. 683-0. 761), and better performance when compared to other methods.
Mitosis domain generalization in histopathology images -- The MIDOG challenge
The goal of the MICCAI MIDOG 2021 challenge has been to propose and evaluate methods that counter this domain shift and derive scanner-agnostic mitosis detection algorithms.
Generating Privacy-Preserving Process Data with Deep Generative Models
We experimented with different models of representation learning and used the learned model to generate synthetic process data.
A Deep Learning Framework for Nuclear Segmentation and Classification in Histopathological Images
Nucleus segmentation and classification are the prerequisites in the workflow of digital pathology processing.
Do Prompts Solve NLP Tasks Using Natural Language?
Thanks to the advanced improvement of large pre-trained language models, prompt-based fine-tuning is shown to be effective on a variety of downstream tasks.
Adversarial Contrastive Self-Supervised Learning
Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention.
Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation
Our results show that Tzer substantially outperforms existing fuzzing techniques on tensor compiler testing, with 75% higher coverage and 50% more valuable tests than the 2nd-best technique.
OpenKBP-Opt: An international and reproducible evaluation of 76 knowledge-based planning pipelines
The dose predictions were input to four optimization models to form 76 unique KBP pipelines that generated 7600 plans.
Multi-task Pre-training Language Model for Semantic Network Completion
To demonstrate the effectiveness of our method, we conduct extensive experiments on three widely-used datasets, WN18RR, FB15k-237, and UMLS.
Ranked #1 on
Link Prediction
on UMLS
Node-Aligned Graph Convolutional Network for Whole-Slide Image Representation and Classification
In this paper, we propose a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) to represent WSI with rich local structural information as well as global distribution.
TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework
Predictor-based Neural Architecture Search (NAS) continues to be an important topic because it aims to mitigate the time-consuming search procedure of traditional NAS methods.
Ranked #21 on
Neural Architecture Search
on CIFAR-10
Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
This paper presents a new method to solve keypoint detection and instance association by using Transformer.
Ranked #10 on
Multi-Person Pose Estimation
on MS COCO
Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.
ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies
Designing neural architectures requires immense manual efforts.
Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices
In this paper, we present a unified framework with Joint Channel pruning and Weight pruning (JCW), and achieves a better Pareto-frontier between the latency and accuracy than previous model compression approaches.
Investigating Non-local Features for Neural Constituency Parsing
Besides, our method achieves state-of-the-art BERT-based performance on PTB (95. 92 F1) and strong performance on CTB (92. 31 F1).
Ranked #6 on
Constituency Parsing
on Penn Treebank
Deep Learning Model for Demodulation Reference Signal based Channel Estimation
In this paper, we propose a deep learning model for Demodulation Reference Signal (DMRS) based channel estimation task.
SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
Recently, x-vector has been a successful and popular approach for speaker verification, which employs a time delay neural network (TDNN) and statistics pooling to extract speaker characterizing embedding from variable-length utterances.
Ranked #1 on
Speaker Verification
on VoxCeleb1
GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization
During the training process, the polarization effect will drive a subset of gates to smoothly decrease to exact zero, while other gates gradually stay away from zero by a large margin.
Sk-Unet Model with Fourier Domain for Mitosis Detection
Mitotic count is the most important morphological feature of breast cancer grading.
Shifted Chunk Transformer for Spatio-Temporal Representational Learning
However, the pure-Transformer based spatio-temporal learning can be prohibitively costly on memory and computation to extract fine-grained features from a tiny patch.
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.
POSO: Personalized Cold Start Modules for Large-scale Recommender Systems
Moreover, POSO can be further generalized to regular users, inactive users and returning users (+2%-3% on Watch Time), as well as item cold start (+3. 8% on Watch Time).
Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department.
SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance.
FINT: Field-aware INTeraction Neural Network For CTR Prediction
As a critical component for online advertising and marking, click-through rate (CTR) prediction has draw lots of attentions from both industry and academia field.
BAGUA: Scaling up Distributed Learning with System Relaxations
Recent years have witnessed a growing list of systems for distributed data-parallel training.
Template-Based Named Entity Recognition Using BART
To address the issue, we propose a template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively.
TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints.
TransPose: Keypoint Localization via Transformer
While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear.
Ranked #3 on
Pose Estimation
on OCHuman
(Validation AP metric)
Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from audio stream
Previous end-to-end SLU models are primarily used for English environment due to lacking large scale SLU dataset in Chines, and use only one ASR model to extract features from speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
What Have We Achieved on Text Summarization?
Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years.
Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification
The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language.
Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge
In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR.
Event Arguments Extraction via Dilate Gated Convolutional Neural Network with Enhanced Local Features
However, the F-Score of event arguments extraction is much lower than that of event trigger extraction, i. e. in the most recent work, event trigger extraction achieves 80. 7%, while event arguments extraction achieves only 58%.
Making the Best Use of Review Summary for Sentiment Analysis
In this paper, we conduct a study to exploit methods for better use of summary information.
Pose Neural Fabrics Search
Neural Architecture Search (NAS) technologies have emerged in many domains to jointly learn the architectures and weights of the neural network.
Ranked #13 on
Keypoint Detection
on MS COCO
Exploring Pre-trained Language Models for Event Extraction and Generation
Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size.
On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization
Recent developments on large-scale distributed machine learning applications, e. g., deep neural networks, benefit enormously from the advances in distributed non-convex optimization techniques, e. g., distributed Stochastic Gradient Descent (SGD).
Shrinking the Upper Confidence Bound: A Dynamic Product Selection Problem for Urban Warehouses
In this paper, we study algorithms for dynamically identifying a large number of products (i. e., SKUs) with top customer purchase probabilities on the fly, from an ocean of potential products to offer on retailers' ultra-fast delivery platforms.
Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning
Ideally, parallel mini-batch SGD can achieve a linear speed-up of the training time (with respect to the number of workers) compared with SGD over a single worker.
Learning with Non-Convex Truncated Losses by SGD
Learning with a {\it convex loss} function has been a dominating paradigm for many years.
Process-oriented Iterative Multiple Alignment for Medical Process Mining
We applied PIMA to analyzing medical workflow data, showing how iterative alignment can better represent the data and facilitate the extraction of insights from data visualization.
Multi-task Vector Field Learning
MTVFL has the following key properties: (1) the vector fields we learned are close to the gradient fields of the prediction functions; (2) within each task, the vector field is required to be as parallel as possible which is expected to span a low dimensional subspace; (3) the vector fields from all tasks share a low dimensional subspace.
Fused Multiple Graphical Lasso
We expect the two brain networks for NC and MCI to share common structures but not to be identical to each other; similarly for the two brain networks for MCI and AD.
