Search Results for author:
Found 50 papers, 20 papers with code
Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT
We also apply an imitation learning strategy to augment a reasonable amount of pseudo APE training data, potentially preventing the model to overfit on the limited real training data and boosting the performance on held-out data.
Alibaba Submission to the WMT20 Parallel Corpus Filtering Task
In the filtering task, three main methods are applied to evaluate the quality of the parallel corpus, i. e. a) Dual Bilingual GPT-2 model, b) Dual Conditional Cross-Entropy Model and c) IBM word alignment model.
TermMind: Alibaba’s WMT21 Machine Translation Using Terminologies Task Submission
We used tags to mark and add the term translations into the matched sentences.
QEMind: Alibaba’s Submission to the WMT21 Quality Estimation Shared Task
Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years.
Transformer representation learning is necessary for dynamic multi-modal physiological data on small-cohort patients
Postoperative delirium (POD), a severe neuropsychiatric complication affecting nearly 50% of high-risk surgical patients, is defined as an acute disorder of attention and cognition, It remains significantly underdiagnosed in the intensive care units (ICUs) due to subjective monitoring methods.
Goku: Flow Based Video Generative Foundation Models
This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance.
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
This work identifies the Energy Loss Phenomenon in Reinforcement Learning from Human Feedback (RLHF) and its connection to reward hacking.
Visualizing the Local Atomic Environment Features of Machine Learning Interatomic Potential
This paper addresses the challenges of creating efficient and high-quality datasets for machine learning potential functions.
ILETIA: An AI-enhanced method for individualized trigger-oocyte pickup interval estimation of progestin-primed ovarian stimulation protocol
In vitro fertilization-embryo transfer (IVF-ET) stands as one of the most prevalent treatments for infertility.
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction.
A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation
The first step is called reconstruction reflection.
Creating a Microstructure Latent Space with Rich Material Information for Multiphase Alloy Design
By integrating this deep learning model with a specific sampling strategy in the latent space, a novel, microstructure-centered algorithm for multiphase alloy design is developed.
Mamba2MIL: State Space Duality Based Multiple Instance Learning for Computational Pathology
Existing frameworks, such as those based on Convolutional Neural Networks (CNNs), attention, and selective scan space state sequential model (SSM), lack sufficient flexibility and scalability in fusing diverse features, and cannot effectively fuse diverse features.
SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Generation
Recent style transfer problems are still largely dominated by Generative Adversarial Network (GAN) from the perspective of cross-domain image-to-image (I2I) translation, where the pivotal issue is to learn and transfer target-domain style patterns onto source-domain content images.
Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery
We then introduce a novel cross-view instance label grouping strategy based on the 3D scene representation to mitigate the multi-view inconsistency problem in the 2D instance labels.
Learning to Manipulate Artistic Images
Recent advancement in computer vision has significantly lowered the barriers to artistic creation.
Intention Analysis Makes LLMs A Good Jailbreak Defender
Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that $\mathbb{IA}$ could consistently and significantly reduce the harmfulness in responses (averagely -48. 2% attack success rate).
Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency
3D visual grounding plays a crucial role in scene understanding with extensive applications in AR/VR.
Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting
In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the performance with prompting.
Synslator: An Interactive Machine Translation Tool with Online Learning
Interactive machine translation (IMT) has emerged as a progression of the computer-aided translation paradigm, where the machine translation system and the human translator collaborate to produce high-quality translations.
Learning Efficient Representations for Image-Based Patent Retrieval
Patent retrieval has been attracting tremendous interest from researchers in intellectual property and information retrieval communities in the past decades.
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words.
Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras.
Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning
In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training).
Disambiguated Lexically Constrained Neural Machine Translation
Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications.
Non-parametric, Nearest-neighbor-assisted Fine-tuning for Neural Machine Translation
We explore whether such non-parametric models can improve machine translation models at the fine-tuning stage by incorporating statistics from the kNN predictions to inform the gradient updates for a baseline translation model.
Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Features
Based on this hybrid representation, we propose a fast optimization NeRF variant, called GP-NeRF, that achieves better rendering results while maintaining a compact model size.
EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography
The EDMAE encoder is composed of a teacher and a student encoder.
TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task
The leader board finally shows that our submissions are ranked first in three of four language directions in the Naive TS task of the WMT22 Translation Suggestion task.
Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation
Human translators perform post editing on machine translations to correct errors in the scene of computer aided translation.
Third-Party Aligner for Neural Word Alignments
Word alignment is to find translationally equivalent words between source and target sentences.
Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
Image cartoonization is recently dominated by generative adversarial networks (GANs) from the perspective of unsupervised image-to-image translation, in which an inherent challenge is to precisely capture and sufficiently transfer characteristic cartoon styles (e. g., clear edges, smooth color shading, abstract fine structures, etc.).
Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space
In Ada-NETS, each face is transformed to a new structure space, obtaining robust features by considering face features of the neighbour images.
QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task
Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years.
Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation
Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT).
Graph Convolution for Re-ranking in Person Re-identification
In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
Bilingual Terminology Extraction from Comparable E-Commerce Corpora
Bilingual terminologies are important machine translation resources in the field of e-commerce, which are usually either manually translated or automatically extracted from parallel data.
1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking
We extend the classical tracking-by-detection paradigm to this tracking-any-object task.
Ranked #9 on
Multi-Object Tracking
on TAO
(using extra training data)
1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation
To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses.
Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations
Place is an important element in visual understanding.
Multi-Domain Learning and Identity Mining for Vehicle Re-Identification
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
From Trailers to Storylines: An Efficient Way to Learn from Movies
Experiments on this dataset showed that the proposed method can substantially reduce the training time while obtaining highly effective features and coherent temporal structures.
Detecting Visual Relationships with Deep Relational Networks
Relationships among objects play a crucial role in image understanding.
