Search Results for author:
Found 79 papers, 28 papers with code
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks.
Ranked #281 on
Image Classification
on ImageNet
SepViT: Separable Vision Transformer
Vision Transformers have witnessed prevailing success in a series of vision tasks.
Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
By evaluating on a number of benchmark test sets, we find that ChatGPT performs competitively with commercial translation products (e. g., Google Translate) on high-resource European languages but lags behind significantly on low-resource or distant languages.
Exploring Human-Like Translation Strategy with Large Language Models
Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process which might take preparatory steps to ensure high-quality translation.
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution.
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback
Therefore, we propose ParroT, a framework to enhance and regulate the translation abilities during chat based on open-source LLMs (e. g., LLaMA), human-written translation and feedback data.
DrugAssist: A Large Language Model for Molecule Optimization
Recently, the impressive performance of large language models (LLMs) on a wide range of tasks has attracted an increasing number of attempts to apply LLMs in drug discovery.
VmambaIR: Visual State Space Model for Image Restoration
To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks.
Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation
By carefully designing experiments, we identify two representative characteristics of the data gap in source: (1) style gap (i. e., translated vs. natural text style) that leads to poor generalization capability; (2) content gap that induces the model to produce hallucination content biased towards the target language.
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation
In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data.
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
Decision-making, a complicated task requiring various types of abilities, presents an excellent framework for assessing Large Language Models (LLMs).
How Does Selective Mechanism Improve Self-Attention Networks?
Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words.
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation
First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities.
Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task
Finally, our unconstrained system achieves BLEU scores of 17. 0 and 30. 4 for English to/from Livonian.
MoCoViT: Mobile Convolutional Vision Transformer
Recently, Transformer networks have achieved impressive results on a variety of vision tasks.
Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training.
Tencent AI Lab Machine Translation Systems for the WMT20 Biomedical Translation Task
This paper describes the Tencent AI Lab submission of the WMT2020 shared task on biomedical translation in four language directions: German<->English, English<->German, Chinese<->English and English<->Chinese.
Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models
Ideally, an advanced agent should possess the ability to accurately describe a given word using an aggressive description while concurrently maximizing confusion in the conservative description, enhancing its participation in the game.
Cross-modality Data Augmentation for End-to-End Sign Language Translation
It has been a challenging task due to the modality gap between sign videos and texts and the data scarcity of labeled data.
Ranked #3 on
Sign Language Translation
on CSL-Daily
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.
Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction
First, we apply adaptive hybrid graph learning to learn the compound spatial correlations among cell towers.
Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation
In this paper, to overcome the limitation, we propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale in-domain spoken language text data.
Forward Learning of Graph Neural Networks
To address these limitations, the forward-forward algorithm (FF) was recently proposed as an alternative to BP in the image classification domain, which trains NNs by performing two forward passes over positive and negative data.
STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction
The approach first classifies the auto-annotated instances into two groups: confident instances and uncertain instances, according to the probabilities predicted by a teacher model.
Cross-Drone Transformer Network for Robust Single Object Tracking
During the tracking process, a cross-drone mapping mechanism is proposed by using the surrounding information of the drone with promising tracking status as reference, assisting drones that lost targets to re-calibrate, which implements real-time cross-drone information interaction.
GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection
The choice of a graph learning (GL) model (i. e., a GL algorithm and its hyperparameter settings) has a significant impact on the performance of downstream tasks.
Cross-Resolution Land Cover Classification Using Outdated Products and Transformers
In this paper, we propose a Transformerbased weakly supervised method for cross-resolution land cover classification using outdated data.
Translating Phrases in Neural Machine Translation
Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does.
Neural Machine Translation Advised by Statistical Machine Translation
Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years.
Scalable Compression of Deep Neural Networks
Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems.
Network Modeling and Pathway Inference from Incomplete Data ("PathInf")
In this work, we developed a network inference method from incomplete data ("PathInf") , as massive and non-uniformly distributed missing values is a common challenge in practical problems.
Exploiting Deep Representations for Neural Machine Translation
Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures.
Learning to Refine Source Representations for Neural Machine Translation
Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process.
Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement
With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation.
Context-Aware Self-Attention Networks
Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies.
Information Aggregation for Multi-Head Attention with Routing-by-Agreement
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces.
Modeling Recurrence for Transformer
In addition to the standard recurrent neural network, we introduce a novel attentive recurrent network to leverage the strengths of both attention and recurrent networks.
Multiple Independent Subspace Clusterings
To ease this process, we consider diverse clusterings embedded in different subspaces, and analyze the embedding subspaces to shed light into the structure of each clustering.
Exploiting Sentential Context for Neural Machine Translation
In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT).
Towards Understanding Neural Machine Translation with Word Importance
Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory.
One Model to Learn Both: Zero Pronoun Prediction and Translation
In this paper, we propose a unified and discourse-aware ZP translation approach for neural MT models.
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons
Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work.
Multi-Granularity Self-Attention for Neural Machine Translation
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information.
Neuron Interaction Based Representation Composition for Neural Machine Translation
Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e. g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors.
Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models
In this paper, we bridge the gap by assessing the bilingual knowledge learned by NMT models with phrase table -- an interpretable table of bilingual lexicons.
Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search
In this way, PAD-NAS can automatically design the operations for each layer and achieve a trade-off between search space quality and model diversity.
Cross Learning in Deep Q-Networks
In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors.
Reannealing of Decaying Exploration Based On Heuristic Measure in Deep Q-Network
Existing exploration strategies in reinforcement learning (RL) often either ignore the history or feedback of search, or are complicated to implement.
Adaptive Spatial-Temporal Inception Graph Convolutional Networks for Multi-step Spatial-Temporal Network Data Forecasting
Spatial-temporal data forecasting is of great importance for industries such as telecom network operation and transportation management.
Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network
We have proposed to develop a global hybrid deep learning framework to predict the daily prices in the stock market.
Training Recommender Systems at Scale: Communication-Efficient Model and Data Parallelism
This is done by identifying and updating only the most relevant neurons of the neural network for each training sample in the data.
Non-Newtonian and poroelastic effects in simulations of arterial flows
In this paper, we focus on investigating the influence on hydrodynamic factors of different coupled computational models describing the interaction between an incompressible fluid and two symmetric elastic or poroelastic structures.
Fluid Dynamics Numerical Analysis Numerical Analysis
Hierarchical Representation via Message Propagation for Robust Model Fitting
In this paper, we propose a novel hierarchical representation via message propagation (HRMP) method for robust model fitting, which simultaneously takes advantages of both the consensus analysis and the preference analysis to estimate the parameters of multiple model instances from data corrupted by outliers, for robust model fitting.
Benchmarking Graph Neural Networks on Link Prediction
In this paper, we benchmark several existing graph neural network (GNN) models on different datasets for link predictions.
TranSmart: A Practical Interactive Machine Translation System
Automatic machine translation is super efficient to produce translations yet their quality is not guaranteed.
Failure-averse Active Learning for Physics-constrained Systems
Active learning is a subfield of machine learning that is devised for design and modeling of systems with highly expensive sampling costs.
Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting.
Tencent Neural Machine Translation Systems for the WMT20 News Translation Task
This paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks.
Tencent AI Lab Machine Translation Systems for WMT20 Chat Translation Task
This paper describes the Tencent AI Lab’s submission of the WMT 2020 shared task on chat translation in English-German.
Geometry-Aware Fruit Grasping Estimation for Robotic Harvesting in Orchards
It is vital for robots to recognise and localise fruits before the harvesting in natural orchards.
Tencent Translation System for the WMT21 News Translation Task
Based on our success in the last WMT, we continuously employed advanced techniques such as large batch training, data selection and data filtering.
Tencent AI Lab Machine Translation Systems for the WMT21 Biomedical Translation Task
This paper describes the Tencent AI Lab submission of the WMT2021 shared task on biomedical translation in eight language directions: English-German, English-French, English-Spanish and English-Russian.
Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation
In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT).
Network Topology Optimization via Deep Reinforcement Learning
A2C-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL actor layer to conduct a topology search.
TRT-ViT: TensorRT-oriented Vision Transformer
We revisit the existing excellent Transformers from the perspective of practical application.
Sepsis Prediction with Temporal Convolutional Networks
We design and implement a temporal convolutional network model to predict sepsis onset.
Asynchronous Hierarchical Federated Learning
Federated Learning is a rapidly growing area of research and with various benefits and industry applications.
Semantic Segmentation of Fruits on Multi-sensor Fused Data in Natural Orchards
In this work, we propose a deep-learning-based segmentation method to perform accurate semantic segmentation on fused data from a LiDAR-Camera visual sensor.
Hyperbolic Cosine Transformer for LiDAR 3D Object Detection
The cosh-attention module reduces the space and time complexity of the attention operation.
MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting
To capture the intrinsic patterns of time series, we propose a novel deep learning network architecture, named Multi-resolution Periodic Pattern Network (MPPN), for long-term series forecasting.
Fin-QD: A Computational Design Framework for Soft Grippers: Integrating MAP-Elites and High-fidelity FEM
This work first discusses a significantly large design space (28 design parameters) for a finger-based soft gripper, including the rarely-explored design space of finger arrangement that is converted to various configurations to arrange individual soft fingers.
Unsupervised Sign Language Translation and Generation
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data.
Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
Furthermore, we analyze two key factors that contribute to the cross-lingual consistency in text watermarking and propose a defense method that increases the AUC from 0. 67 to 0. 88 under CWRA.
InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting
A channel identifier, a global mixing module and a self-contextual attention module are devised in InjectTST.
StreakNet-Arch: An Anti-scattering Network-based Architecture for Underwater Carrier LiDAR-Radar Imaging
In this paper, we introduce StreakNet-Arch, a novel signal processing architecture designed for Underwater Carrier LiDAR-Radar (UCLR) imaging systems, to address the limitations in scatter suppression and real-time imaging.
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation; and ii) ODE Trajectory Reformulation.
