Search Results for author:
Found 77 papers, 19 papers with code
Where to Attack: A Dynamic Locator Model for Backdoor Attack in Text Classifications
Based on the predicted P2P, four effective strategies are introduced to show the BDA performance.
Data-driven topology design based on principal component analysis for 3D structural design problems
Topology optimization is a structural design methodology widely utilized to address engineering challenges.
ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model
Finally, to mitigate the hallucinations of ChipExpert, we have developed a Retrieval-Augmented Generation (RAG) system, based on the IC design knowledge base.
RepoQA: Evaluating Long Context Code Understanding
Recent advances have been improving the context windows of Large Language Models (LLMs).
NeB-SLAM: Neural Blocks-based Salable RGB-D SLAM for Unknown Scenes
However, these methods necessitate the size of the scene as input, which is impractical for unknown scenes.
Efficient Multi-agent Reinforcement Learning by Planning
Extensive experiments on the SMAC benchmark demonstrate that MAZero outperforms model-free approaches in terms of sample efficiency and provides comparable or better performance than existing model-based methods in terms of both sample and computational efficiency.
Computational Efficiency
Model-based Reinforcement Learning
+2
Tailoring Vaccine Messaging with Common-Ground Opinions
We define the task of tailoring vaccine interventions to a Common-Ground Opinion (CGO).
Auto-Optimized Maximum Torque Per Ampere Control of IPMSM Using Dual Control for Exploration and Exploitation
In this paper, a maximum torque per ampere (MTPA) control strategy for the interior permanent magnet synchronous motor (IPMSM) using dual control for exploration and exploitation (DCEE).
Harnessing Optical Imaging Limit through Atmospheric Scattering Media
Recording and identifying faint objects through atmospheric scattering media by an optical system are fundamentally interesting and technologically important.
ScaleFold: Reducing AlphaFold Initial Training Time to 10 Hours
In this work, we conducted a comprehensive analysis on the AlphaFold training procedure based on Openfold, identified that inefficient communications and overhead-dominated computations were the key factors that prevented the AlphaFold training from effective scaling.
Texture Classification Network Integrating Adaptive Wavelet Transform
Graves' disease is a common condition that is diagnosed clinically by determining the smoothness of the thyroid texture and its morphology in ultrasound images.
Diverse and Lifespan Facial Age Transformation Synthesis with Identity Variation Rationality Metric
Face aging has received continuous research attention over the past two decades.
Selective-Memory Meta-Learning with Environment Representations for Sound Event Localization and Detection
In addition, we introduce environment representations to characterize different acoustic settings, enhancing the adaptability of our attenuation approach to various environments.
Efficient Title Reranker for Fast and Improved Knowledge-Intense NLP
This results in high computational costs and limits the number of retrieved text, hindering accuracy.
Superpixel Semantics Representation and Pre-training for Vision-Language Task
To capture superpixel-level semantic features, we propose a Multiscale Difference Graph Convolutional Network (MDGCN).
Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors
Unlike current state-of-the-art approaches, we explicitly model the uncertainty of the object shapes and poses during our optimization, resulting in a high-quality object-level mapping system.
META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection
For learning-based sound event localization and detection (SELD) methods, different acoustic environments in the training and test sets may result in large performance differences in the validation and evaluation stages.
Variational Label-Correlation Enhancement for Congestion Prediction
In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, {\ours}, i. e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids.
Rethinking PRL: A Multiscale Progressively Residual Learning Network for Inverse Halftoning
Because the halftone images lose much of the original image content, inverse halftoning is a classic ill-problem.
Learning Diverse Risk Preferences in Population-based Self-play
In this paper, we aim to introduce diversity from the perspective that agents could have diverse risk preferences in the face of uncertainty.
Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning
To empirically show the advantages of TATU, we first combine it with two classical model-based offline RL algorithms, MOPO and COMBO.
Task-oriented Memory-efficient Pruning-Adapter
Adapters are to freeze the model and give it a new weight matrix on the side, which can significantly reduce the time and memory of training, but the cost is that the evaluation and testing will increase the time and memory consumption.
Pixel Difference Convolutional Network for RGB-D Semantic Segmentation
For the Depth branch, we propose a Pixel Difference Convolution (PDC) to consider local and detailed geometric information in Depth data via aggregating both intensity and gradient information.
Ranked #16 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Selective Noise Suppression Methods Using Random SVPWM to Shape the Noise Spectrum of PMSMs
Both the pulse position and switching frequency are randomized in the second method.
Dual Control of Exploration and Exploitation for Auto-Optimisation Control with Active Learning
Formal properties of the proposed DCEE framework like convergence are established.
Edge Enhanced Image Style Transfer via Transformers
In recent years, arbitrary image style transfer has attracted more and more attention.
Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation
Previous attacks assume the adversary can infer the local learning rate of each client, while we observe that: (1) using the uniformly distributed random local learning rates does not incur much accuracy loss of the global model, and (2) personalizing local learning rates can mitigate the drift issue which is caused by non-IID (identically and independently distributed) data.
Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery
We show that such lossless primitives can drastically improve the performance of hierarchical policies.
Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox
With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems.
S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention
Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling.
DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation
A two-branch network built with DCA and EDCA, called Differential Convolutional Network (DCANet), is proposed to fuse local and global information of two-modal data.
Ranked #16 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
SmartFPS: Neural Network based Wireless-inertial fusion positioning system
The current fusion positioning systems are mainly based on filtering algorithms, such as Kalman filtering or particle filtering.
Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains
Our system submitted to the DCASE 2022 Task 3 is based on our previous proposed Event-Independent Network V2 (EINV2) with a novel data augmentation method.
Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics
The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory.
Stereographic Markov Chain Monte Carlo
High-dimensional distributions, especially those with heavy tails, are notoriously difficult for off-the-shelf MCMC samplers: the combination of unbounded state spaces, diminishing gradient information, and local moves results in empirically observed ``stickiness'' and poor theoretical mixing properties -- lack of geometric ergodicity.
IR-ORAM: Path Access Type Based Memory Intensity Reduction for Path-ORAM
We develop a set of techniques to reduce the memory intensity of each type while ensuring the obliviousness at the same time — we reduce the number of data blocks to access for each tree path, reduce the number of path accesses for position maps, and convert many dummy path accesses to early write-backs of dirty data in LLC.
Improved Multi-step FCS-MPCC with Disturbance Compensation for PMSM Drives -- Methods and Experimental Validation
In this paper, an improved multi-step finite control set model predictive current control (FCS-MPCC) strategy with speed loop disturbance compensation is proposed for permanent magnet synchronous machine (PMSM) drives system.
A distributionally robust optimization approach to two-sided chance constrained stochastic model predictive control with unknown noise distribution
In this work, we propose a distributionally robust stochastic model predictive control (DR-SMPC) algorithm to address the problem of two-sided chance constrained discrete-time linear system corrupted by additive noise.
Multi-step dual control for exploration and exploitation in autonomous search with convergence guarantee
Motivated by the recently proposed dual control for exploration and exploitation (DCEE) concept, this paper presents a Multi-Step DCEE (MS-DCEE) framework with guaranteed convergence for autonomous search of a source of airborne dispersion.
Next-Best-View Prediction for Active Stereo Cameras and Highly Reflective Objects
Depth acquisition with the active stereo camera is a challenging task for highly reflective objects.
AI in Human-computer Gaming: Techniques, Challenges and Opportunities
Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs.
Exposing Deepfake with Pixel-wise AR and PPG Correlation from Faint Signals
This scheme extracts two types of minute information hidden between face pixels-photoplethysmography (PPG) features and auto-regressive (AR) features, which are used as the basis for forensics in the temporal and spatial domains, respectively.
Offline Reinforcement Learning with Value-based Episodic Memory
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data.
Safe Opponent-Exploitation Subgame Refinement
Search algorithms have been playing a vital role in the success of superhuman AI in both perfect information and imperfect information games.
Concurrent Active Learning in Autonomous Airborne Source Search: Dual Control for Exploration and Exploitation
In this setting, the control action not only minimises the tracking error between future agent's position and estimated source location, but also the uncertainty of predicted estimation.
Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Reinforcement learning (RL)-based auto-pruning has been further proposed to automate the DNN pruning process to avoid expensive hand-crafted work.
Average-Reward Reinforcement Learning with Trust Region Methods
Our work provides a unified framework of the trust region approach including both the discounted and average criteria, which may complement the framework of reinforcement learning beyond the discounted objectives.
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
Moreover, we extend ICQ to multi-agent tasks by decomposing the joint-policy under the implicit constraint.
Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks.
You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Motivated by the necessity of efficient inference across various constraints on BERT, we propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere.
Dual-Stage Low-Complexity Reconfigurable Speech Enhancement
This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources.
Compact Dual-Polarization Silicon Integrated Couplers for Multicore Fibers
Compact fiber-to-chip couplers play an important role in optical interconnections, especially in data centers.
Optics Applied Physics
Acoustic Structure Inverse Design and Optimization Using Deep Learning
From ancient to modern times, acoustic structures have been used to control the propagation of acoustic waves.
Phase Shift of Planetary Waves and Wave--Jet Resonance on Tidally Locked Planets
This study improves the understanding of wave--mean flow interactions on tidally locked planets.
Atmospheric and Oceanic Physics Earth and Planetary Astrophysics Fluid Dynamics
INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devices
The intensive computation of Automatic Speech Recognition (ASR) models obstructs them from being deployed on mobile devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Wavelet-CNN-LSTM Model for Tailings Pond Risk Prediction
Tailings ponds are places for storing industrial waste.
FusionStitching: Boosting Memory Intensive Computations for Deep Learning Workloads
We show in this work that memory intensive computations can result in severe performance problems due to off-chip memory access and CPU-GPU context switch overheads in a wide range of deep learning models.
Active Disturbance Rejection Control Design with Suppression of Sensor Noise Effects in Application to DC-DC Buck Power Converter
The performance of active disturbance rejection control (ADRC) algorithms can be limited in practice by high-frequency measurement noise.
Intelligent Optimization of Diversified Community Prevention of COVID-19 using Traditional Chinese Medicine
First, we use a fuzzy clustering method to divide the population based on both modern medicine and TCM health characteristics; we then use an interactive optimization method, in which TCM experts develop different TCM prevention programs for different clusters, and a heuristic algorithm is used to optimize the programs under the resource constraints.
Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
The last decade has witnessed growth in the computational requirements for training deep neural networks.
SOAC: The Soft Option Actor-Critic Architecture
In these tasks, our approach learns a diverse set of options, each of whose state-action space has strong coherence.
Ansor: Generating High-Performance Tensor Programs for Deep Learning
Ansor can find high-performance programs that are outside the search space of existing state-of-the-art approaches.
Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration
The generative adversarial imitation learning (GAIL) has provided an adversarial learning framework for imitating expert policy from demonstrations in high-dimensional continuous tasks.
DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging
The state-of-the-art deep learning algorithms rely on distributed training systems to tackle the increasing sizes of models and training data sets.
DSAC: Distributional Soft Actor Critic for Risk-Sensitive Reinforcement Learning
In this paper, we present a new reinforcement learning (RL) algorithm called Distributional Soft Actor Critic (DSAC), which exploits the distributional information of accumulated rewards to achieve better performance.
Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling
The advantage of this method is to make the model converge to various local optima by scheduling the learning rate in once training.
Characterizing Deep Learning Training Workloads on Alibaba-PAI
One critical issue for efficiently operating practical AI clouds, is to characterize the computing and data transfer demands of these workloads, and more importantly, the training performance given the underlying software framework and hardware configurations.
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
The developments of Rademacher complexity and PAC-Bayesian theory have been largely independent.
Efficient Knowledge Graph Accuracy Evaluation
To address the problem, this paper proposes an efficient sampling and evaluation framework, which aims to provide quality accuracy evaluation with strong statistical guarantee while minimizing human efforts.
Databases
A Novel Integrated Framework for Learning both Text Detection and Recognition
In this paper, we propose a novel integrated framework for learning both text detection and recognition.
Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks
In this method, the network is viewed as a computational graph, in which the vertices denote the computation nodes and edges represent the information flow.
Pyramid Embedded Generative Adversarial Network for Automated Font Generation
The generator is built using one encoder-decoder structure with cascaded refinement connections and mirror skip connections.
FusionStitching: Deep Fusion and Code Generation for Tensorflow Computations on GPUs
In recent years, there is a surge on machine learning applications in industry.
Distributed, Parallel, and Cluster Computing Mathematical Software
Wearable Affective Robot
The learning algorithm for the life modeling embedded in Fitbot can achieve better user's experience of affective social interaction.
Electroencephalogram (EEG)
Human-Computer Interaction
Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI
Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions’ locations.
Towards well-specified semi-supervised model-based classifiers via structural adaptation
This issue is known as model misspecification.
NV-Tree: Reducing Consistency Cost for NVM-based Single Level Systems
Although the memory fence and CPU cacheline flush instructions can order memory writes to achieve data consistency, they introduce a significant overhead (more than 10X slower in performance).
