Search Results for author:
Found 72 papers, 21 papers with code
CSP:Code-Switching Pre-training for Neural Machine Translation
Unlike traditional pre-training method which randomly masks some fragments of the input sentence, the proposed CSP randomly replaces some words in the source sentence with their translation words in the target language.
Exploring and Evaluating Hallucinations in LLM-Powered Code Generation
The rise of Large Language Models (LLMs) has significantly advanced many applications on software engineering tasks, particularly in code generation.
ACMI: An index for exposed coal mapping using Landsat imagery
The default threshold makes EC mapping using ACMI an automated process.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we present the latest model of the Gemini family, Gemini 1. 5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #19 on
Code Generation
on HumanEval
Does Negative Sampling Matter? A Review with Insights into its Theory and Applications
Is there a general framework that can incorporate all existing negative sampling methods?
TriSampler: A Better Negative Sampling Principle for Dense Retrieval
Negative sampling stands as a pivotal technique in dense retrieval, essential for training effective retrieval models and significantly impacting retrieval performance.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models
Specifically, for the input from any modality, TEAL first discretizes it into a token sequence with the off-the-shelf tokenizer and embeds the token sequence into a joint embedding space with a learnable embedding matrix.
Object-aware Inversion and Reassembly for Image Editing
Subsequently, we propose an additional reassembly step to seamlessly integrate the respective editing results and the non-editing region to obtain the final edited image.
XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners
Active learning (AL), which aims to construct an effective training set by iteratively curating the most formative unlabeled data for annotation, has been widely used in low-resource tasks.
Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information
However, we observe that merely concatenating sentences in a contextual window does not fully utilize contextual information and can sometimes lead to excessive attention on less informative sentences.
GPT Can Solve Mathematical Problems Without a Calculator
Previous studies have typically assumed that large language models are unable to accurately perform arithmetic operations, particularly multiplication of >8 digits, and operations involving decimals and fractions, without the use of calculator tools.
ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation
Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of vision-language tasks.
Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling
In order to coordinate energy interactions among various communities and energy conversions among multi-energy subsystems within the multi-community integrated energy system under uncertain conditions, and achieve overall optimization and scheduling of the comprehensive energy system, this paper proposes a comprehensive scheduling model that utilizes a multi-agent deep reinforcement learning algorithm to learn load characteristics of different communities and make decisions based on this knowledge.
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge.
BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs
To make each mini-batch have fewer false negatives, we design the proximity graph of randomly-selected instances.
LoRAPrune: Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning
This is due to their utilization of unstructured pruning on LPMs, impeding the merging of LoRA weights, or their dependence on the gradients of pre-trained weights to guide pruning, which can impose significant memory overhead.
Advances and Challenges of Multi-task Learning Method in Recommender System: A Survey
Multi-task learning has been widely applied in computational vision, natural language processing and other fields, which has achieved well performance.
Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion
It is seldom considered to adapt the decision boundary for new representations and in this paper we propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning (SCCL), In our method, a contrastive loss is used to directly learn representations for different tasks and a limited number of data samples are saved as the classification criterion.
Investigating Forgetting in Pre-Trained Representations Through Continual Learning
Intuitively, the representation forgetting can influence the general knowledge stored in pre-trained language models (LMs), but the concrete effect is still unclear.
Causal Interventions-based Few-Shot Named Entity Recognition
Few-shot named entity recognition (NER) systems aims at recognizing new classes of entities based on a few labeled samples.
CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data
Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks.
Ranked #3 on
Zero-shot 3D Point Cloud Classification
on ScanNetV2
The Graph feature fusion technique for speaker recognition based on wav2vec2.0 framework
The GNN takes all the output features as the graph signal data and extracts the related graph structure information of features for speaker recognition.
Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View
Based on the covariate shift assumption, we find that the gap mainly attributes to the feature distribution of BEV, which is determined by the quality of both depth estimation and 2D image's feature representation.
CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data
Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks.
An open unified deep graph learning framework for discovering drug leads
However, this is non-ideal, as clumsy integration of incompatible models increases research overheads, and may even reduce success rates in drug discovery.
Findings of the WMT 2022 Shared Task on Translation Suggestion
We report the result of the first edition of the WMT shared task on Translation Suggestion (TS).
Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones.
Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment
Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing.
Rethink about the Word-level Quality Estimation for Machine Translation from Human Judgement
While the post-editing effort can be used to measure the translation quality to some extent, we find it usually conflicts with the human judgement on whether the word is well or poorly translated.
Evaluation of Question Answering Systems: Complexity of judging a natural language
Question answering (QA) systems are among the most important and rapidly developing research topics in natural language processing (NLP).
Protecting World Leader Using Facial Speaking Pattern Against Deepfakes
This paper proposes a dual stream learning facial and speaking patterns method to protect celebrities against deepfakes.
ONCE-3DLanes: Building Monocular 3D Lane Detection
We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space.
Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction.
Universal Graph Filter Design based on Butterworth, Chebyshev and Elliptic Functions
In this paper, we propose to design universal IIR graph filters with low computational complexity by using three kinds of functions, which are Butterworth, Chebyshev, and Elliptic functions, respectively.
Laneformer: Object-aware Row-Column Transformers for Lane Detection
We present Laneformer, a conceptually simple yet powerful transformer-based architecture tailored for lane detection that is a long-standing research topic for visual perception in autonomous driving.
Weighted Mean and Median graph Filters with Attenuation Factor for Sensor Network
This paper proposes a weighted attenuation k-hop graph, which depicts the spatial neighbor nodes with their hops from the central node.
EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation
Complete Multi-lingual Neural Machine Translation (C-MNMT) achieves superior performance against the conventional MNMT by constructing multi-way aligned corpus, i. e., aligning bilingual training examples from different language pairs when either their source or target sides are identical.
TSAM: A Two-Stream Attention Model for Causal Emotion Entailment
Causal Emotion Entailment (CEE) aims to discover the potential causes behind an emotion in a conversational utterance.
Ranked #3 on
Causal Emotion Entailment
on RECCON
Optimal Fractional Fourier Filtering in Time-vertex Graphs signal processing
Furthermore, the optimal time-vertex graph filter in fractional domains is also developed, using the graph fractional Laplacian operator and graph fractional Fourier transform.
Hierarchical Stochastic Scheduling of Multi-Community Integrated Energy Systems in Uncertain Environments via Stackelberg Game
An operating entity utilizing community-integrated energy systems with a large number of small-scale distributed energy sources can easily trade with existing distribution markets.
Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training
First, 3D-CoCo is inspired by our observation that the bird-eye-view (BEV) features are more transferable than low-level geometry features.
Stochastic optimal scheduling of demand response-enabled microgrids with renewable generations: An analytical-heuristic approach
In order to solve this model, this research combines Jaya algorithm and interior point method (IPM) to develop a hybrid analysis-heuristic solution method called Jaya-IPM, where the lower- and upper- levels are respectively addressed by the IPM and the Jaya, and the scheduling scheme is obtained via iterations between the two levels.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
WeTS: A Benchmark for Translation Suggestion
To break this limitation, we create a benchmark data set for TS, called \emph{WeTS}, which contains golden corpus annotated by expert translators on four translation directions.
Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information
However, only using the code snippets in the question body cannot provide sufficient information for title generation, and LSTMs cannot capture the long-range dependencies between tokens.
Optimal Scheduling of Integrated Demand Response-Enabled Community Integrated Energy Systems in Uncertain Environments
The community integrated energy system (CIES) is an essential energy internet carrier that has recently been the focus of much attention.
Optimal Scheduling of Isolated Microgrids Using Automated Reinforcement Learning-based Multi-period Forecasting
In order to reduce the negative impact of the uncertainty of load and renewable energies outputs on microgrid operation, an optimal scheduling model is proposed for isolated microgrids by using automated reinforcement learning-based multi-period forecasting of renewable power generations and loads.
In-depth Analysis of Durations of Discretionary Lane Changes on Freeway Under Varying Traffic Conditions
It was found that the heavy vehicle takes longer time to complete LC maneuver.
Coordinating Flexible Demand Response and Renewable Uncertainties for Scheduling of Community Integrated Energy Systems with an Electric Vehicle Charging Station: A Bi-level Approach
A community integrated energy system (CIES) with an electric vehicle charging station (EVCS) provides a new way for tackling growing concerns of energy efficiency and environmental pollution, it is a critical task to coordinate flexible demand response and multiple renewable uncertainties.
THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS
Our solution focuses on solving two problems in automated audio captioning: data insufficiency and word selection indeterminacy.
Ranked #1 on
Audio captioning
on Clotho
(using extra training data)
Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
Mainstream lane marker detection methods are implemented by predicting the overall structure and deriving parametric curves through post-processing.
Ranked #2 on
Lane Detection
on TuSimple
Active Learning for Lane Detection: A Knowledge Distillation Approach
The experiments show that our method achieves new state-of-the-art on the lane detection benchmarks.
FlowMOT: 3D Multi-Object Tracking by Scene Flow Association
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability.
Manual-Label Free 3D Detection via An Open-Source Simulator
In this paper, we propose a manual-label free 3D detection algorithm that leverages the CARLA simulator to generate a large amount of self-labeled training samples and introduces a novel Domain Adaptive VoxelNet (DA-VoxelNet) that can cross the distribution gap from the synthetic data to the real scenario.
Universal Multi-Source Domain Adaptation
Recent study reveals that knowledge can be transferred from one source domain to another unknown target domain, called Universal Domain Adaptation (UDA).
Multiple Sclerosis Severity Classification From Clinical Text
Next, we present MSBC, a classifier that applies MS-BERT to generate embeddings and predict EDSS and functional subscores.
Bi-GCN: Binary Graph Convolutional Network
Graph Neural Networks (GNNs) have achieved tremendous success in graph representation learning.
Unveiling Class-Labeling Structure for Universal Domain Adaptation
As a more practical setting for unsupervised domain adaptation, Universal Domain Adaptation (UDA) is recently introduced, where the target label set is unknown.
Code-switching pre-training for neural machine translation
Unlike traditional pre-training method which randomly masks some fragments of the input sentence, the proposed CSP randomly replaces some words in the source sentence with their translation words in the target language.
An Iterative Graph Spectral Subtraction Method for Speech Enhancement
In this paper, we investigate the application of graph signal processing (GSP) theory in speech enhancement.
Understanding Negative Sampling in Graph Representation Learning
To the best of our knowledge, we are the first to derive the theory and quantify that the negative sampling distribution should be positively but sub-linearly correlated to their positive sampling distribution.
Metric-Learning-Assisted Domain Adaptation
Domain alignment (DA) has been widely used in unsupervised domain adaptation.
Optimized Energy and Information Relaying in Self-Sustainable IRS-Empowered WPCN
We propose time-switching (TS) and power-splitting (PS) schemes for the IRS, where the IRS can harvest energy from the HAP's signals by switching between energy harvesting and signal reflection in the TS scheme or adjusting its reflection amplitude in the PS scheme.
Entropy Minimization vs. Diversity Maximization for Domain Adaptation
Entropy minimization has been widely used in unsupervised domain adaptation (UDA).
Ranked #6 on
Domain Adaptation
on ImageCLEF-DA
Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions
The new demands for high-reliability and ultra-high capacity wireless communication have led to extensive research into 5G communications.
Semi-Supervised Disfluency Detection
While the disfluency detection has achieved notable success in the past years, it still severely suffers from the data scarcity.
Unsupervised Neural Machine Translation with Weight Sharing
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data.
Ranked #6 on
Machine Translation
on WMT2016 German-English
Learning a Dilated Residual Network for SAR Image Despeckling
In this paper, to break the limit of the traditional linear models for synthetic aperture radar (SAR) image despeckling, we propose a novel deep learning approach by learning a non-linear end-to-end mapping between the noisy and clean SAR images with a dilated residual network (SAR-DRN).
Decorrelation of Neutral Vector Variables: Theory and Applications
In this paper, we propose novel strategies for neutral vector variable decorrelation.
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
During training, both the dynamic discriminator and the static BLEU objective are employed to evaluate the generated sentences and feedback the evaluations to guide the learning of the generator.
A Character-Aware Encoder for Neural Machine Translation
This article proposes a novel character-aware neural machine translation (NMT) model that views the input sequences as sequences of characters rather than words.
