Search Results for author:
Found 60 papers, 21 papers with code
Chinese Grammatical Error Correction Based on Hybrid Models with Data Augmentation
A better Chinese Grammatical Error Diagnosis (CGED) system for automatic Grammatical Error Correction (GEC) can benefit foreign Chinese learners and lower Chinese learning barriers.
Underload: Defending against Latency Attacks for Object Detectors on Edge Devices
Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management.
Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks
Multispectral object detection, utilizing RGB and TIR (thermal infrared) modalities, is widely recognized as a challenging task.
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training
To evaluate the effectiveness of Velocitune, we conduct experiments in a reasoning-focused dataset with CodeLlama, as well as in a corpus specialised for system command generation with Llama3 and Mistral.
No-regret Exploration in Shuffle Private Reinforcement Learning
Previous work mainly focuses on two trust models of DP: the central model, where a central agent is responsible for protecting users' sensitive data, and the (stronger) local model, where the protection occurs directly on the user side.
Privacy-Preserving Resilient Vector Consensus
This paper studies privacy-preserving resilient vector consensus in multi-agent systems against faulty agents, where normal agents can achieve consensus within the convex hull of their initial states while protecting state vectors from being disclosed.
SoK: Dataset Copyright Auditing in Machine Learning Systems
As the implementation of machine learning (ML) systems becomes more widespread, especially with the introduction of larger ML models, we perceive a spring demand for massive data.
Automated Proof Generation for Rust Code via Self-Evolution
Ensuring correctness is crucial for code generation.
SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
LIRE achieves low-overhead vector updates by only reassigning vectors at the boundary between partitions, where in a high-quality vector index the amount of such vectors are deemed small.
Integrative Decoding: Improve Factuality via Implicit Self-consistency
Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models.
FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection
Due to the vast testing space, the increasing demand for effective and efficient testing of deep neural networks (DNNs) has led to the development of various DNN test case prioritization techniques.
Xinyu: An Efficient LLM-based System for Commentary Generation
To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology.
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
Based on the ALIF pipeline, we present the ALIF-OTL and ALIF-OTA schemes for launching attacks in both the digital domain and the physical playback environment on four commercial ASRs and voice assistants.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search
Existing methods based on learning to rank neglect the long-term value of traffic allocation, whereas approaches of reinforcement learning suffer from balancing multiple objectives and the difficulties of cold starts within realworld data environments.
Gradient-Mask Tuning Elevates the Upper Limits of LLM Performance
Large language models (LLMs) have revolutionized lots of fields of research.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Cross-domain-aware Worker Selection with Training for Crowdsourced Annotation
To validate the effectiveness of our methods, we collect two novel real-world datasets and generate synthetic datasets.
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts.
LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models
We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200, 000 tokens.
Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain
In recent years, State Space Models (SSMs) with efficient hardware-aware designs, known as the Mamba deep learning models, have made significant progress in modeling long sequences such as language understanding.
Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering
Especially for the question that require a multi-hop reasoning path, frequent calls to LLM will consume a lot of computing power.
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review
This paper explores the frontiers of large language models (LLMs) in psychology applications.
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation
These techniques encompass the use of directed hallucination induction and strategies that deliberately alter authentic text to produce hallucinations.
Skywork: A More Open Bilingual Foundation Model
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3. 2 trillion tokens drawn from both English and Chinese texts.
FP8-LM: Training FP8 Large Language Models
In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs).
SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
Evaluation results disclose an 88% success rate in bypassing Midjourney's proprietary safety filter with our attack prompts, leading to the generation of counterfeit images depicting political figures in violent scenarios.
ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning
In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL.
Masked Diffusion Models Are Fast Distribution Learners
In the pre-training stage, we propose to mask a high proportion (e. g., up to 90\%) of input images to approximately represent the primer distribution and introduce a masked denoising score matching objective to train a model to denoise visible areas.
Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability. Code is available at: https://github. com/pcheng2/TSRL
Enhancing Cyber-Resiliency of DER-based SmartGrid: A Survey
The overall aim of this survey is to demonstrate the development trend of CRE methods and motivate further efforts to improve the cyber-resiliency of DER-based smart grid.
Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal
Rain-by-snow weather removal is a specialized task in weather-degraded image restoration aiming to eliminate coexisting rain streaks and snow particles.
An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
One of the key challenges in deploying RL to real-world applications is to adapt to variations of unknown environment contexts, such as changing terrains in robotic tasks and fluctuated bandwidth in congestion control.
FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data
Federated learning is a distributed learning that allows each client to keep the original data locally and only upload the parameters of the local model to the server.
Stability of Weighted Majority Voting under Estimated Weights
To formally analyse the uncertainty to the decision process, we introduce and analyse two important properties of such unbiased trust values: stability of correctness and stability of optimality.
Discriminator-Guided Model-Based Offline Imitation Learning
In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations.
Tutel: Adaptive Mixture-of-Experts at Scale
On efficiency, Flex accelerates SwinV2-MoE, achieving up to 1. 55x and 2. 11x speedup in training and inference over Fairseq, respectively.
VeriFi: Towards Verifiable Federated Unlearning
One desirable property for FL is the implementation of the right to be forgotten (RTBF), i. e., a leaving participant has the right to request to delete its private data from the global model.
Spatio-Temporal-Frequency Graph Attention Convolutional Network for Aircraft Recognition Based on Heterogeneous Radar Network
This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network.
GridTuner: Reinvestigate Grid Size Selection for Spatiotemporal Prediction Models [Technical Report]
In this paper, we study a region partitioning problem, namely optimal grid size selection problem (OGSS), which aims to minimize the real error of spatiotemporal prediction models by selecting the optimal grid size.
Semi-Supervised Domain Generalizable Person Re-Identification
Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario.
Ranked #3 on
Person Re-Identification
on Market-1501
(using extra training data)
Generalizable Person Re-identification
Knowledge Distillation
+1
Dynamic Multi-Scale Loss Optimization for Object Detection
With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention.
A Queueing-Theoretic Framework for Vehicle Dispatching in Dynamic Car-Hailing [technical report]
In this paper, we consider an important dynamic car-hailing problem, namely \textit{maximum revenue vehicle dispatching} (MRVD), in which rider requests dynamically arrive and drivers need to serve as many riders as possible such that the entire revenue of the platform is maximized.
CrossoverScheduler: Overlapping Multiple Distributed Training Applications in a Crossover Manner
Distributed deep learning workloads include throughput-intensive training tasks on the GPU clusters, where the Distributed Stochastic Gradient Descent (SGD) incurs significant communication delays after backward propagation, forces workers to wait for the gradient synchronization via a centralized parameter server or directly in decentralized workers.
RobOT: Robustness-Oriented Testing for Deep Learning Systems
A key part of RobOT is a quantitative measurement on 1) the value of each test case in improving model robustness (often via retraining), and 2) the convergence quality of the model robustness improvement.
Software Engineering
TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors
To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural backdoor attacks/defenses in a unified, holistic, and practical manner.
UNIFUZZ: A Holistic and Pragmatic Metrics-Driven Platform for Evaluating Fuzzers
We hope that our findings can shed light on reliable fuzzing evaluation, so that we can discover promising fuzzing primitives to effectively facilitate fuzzer designs in the future.
Cryptography and Security
Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles
We develop a novel hybrid-cascaded deep neural network (DNN) architecture such that the entire system can be optimized in a holistic manner.
FastReID: A Pytorch Toolbox for General Instance Re-identification
General Instance Re-identification is a very important task in the computer vision, which can be widely used in many practical applications, such as person/vehicle re-identification, face recognition, wildlife protection, commodity tracing, and snapshop, etc.. To meet the increasing application demand for general instance re-identification, we present FastReID as a widely used software system in JD AI Research.
Ranked #1 on
Person Re-Identification
on MSMT17-C
Simulating Performance of ML Systems with Offline Profiling
We advocate that simulation based on offline profiling is a promising approach to better understand and improve the complex ML systems.
False Data Injection Attacks and the Distributed Countermeasure in DC Microgrids
In this paper, we consider a hierarchical control based DC microgrid (DCmG) equipped with unknown input observer (UIO) based detectors, where the potential false data injection (FDI) attacks and the distributed countermeasure are investigated.
Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference
Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks.
Reinforcement learning for bandwidth estimation and congestion control in real-time communications
Bandwidth estimation and congestion control for real-time communications (i. e., audio and video conferencing) remains a difficult problem, despite many years of research.
Challenges of Privacy-Preserving Machine Learning in IoT
The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence.
Privacy-preserving Distributed Machine Learning via Local Randomization and ADMM Perturbation
With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks.
A Learning-Based Two-Stage Spectrum Sharing Strategy with Multiple Primary Transmit Power Levels
Then, based on a novel normalized power level alignment metric, we propose two prediction-transmission structures, namely periodic and non-periodic, for spectrum access (the second part in Stage II), which enable the secondary transmitter (ST) to closely follow the PT power level variation.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV
Unmanned Aerial Vehicles (UAVs), have intrigued different people from all walks of life, because of their pervasive computing capabilities.
Focal Loss Dense Detector for Vehicle Surveillance
Deep learning has been widely recognized as a promising approach in different computer vision applications.
