Search Results for author:
Found 436 papers, 124 papers with code
End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose Estimation
To address this phenomenon, we propose a novel end-to-end training scheme that brings the three separate modules into a single model.
Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy
Emotion inference in multi-turn conversations aims to predict the participant’s emotion in the next upcoming turn without knowing the participant’s response yet, and is a necessary step for applications such as dialogue planning.
Public Sentiment Drift Analysis Based on Hierarchical Variational Auto-encoder
Detecting public sentiment drift is a challenging task due to sentiment change over time.
ACFlow: Flow Models for Arbitrary Conditional Likelihoods
However, a majority of generative modeling approaches are focused solely on the joint distribution $p(x)$ and utilize models where it is intractable to obtain the conditional distribution of some arbitrary subset of features $x_u$ given the rest of the observed covariates $x_o$: $p(x_u \mid x_o)$.
LLM-Enhanced Causal Discovery in Temporal Domain from Interventional Data
In the field of Artificial Intelligence for Information Technology Operations, causal discovery is pivotal for operation and maintenance of graph construction, facilitating downstream industrial tasks such as root cause analysis.
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data.
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
We verify the effectiveness of the proposed explanations from two aspects: (1) Counterfactual Trace Visualization: the enhanced forgery images are useful to reveal artifacts by visually contrasting the original images and two different visualization methods; (2) Transferable Adversarial Attacks: the adversarial forgery images generated by attacking the detection model are able to mislead other detection models, implying the removed artifacts are general.
PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer
Amidst the surge in deep learning-based password guessing models, challenges of generating high-quality passwords and reducing duplicate passwords persist.
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
We introduce TableLLM, a robust large language model (LLM) with 13 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios.
NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints.
Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass.
FusionINN: Invertible Image Fusion for Brain Tumor Monitoring
Image fusion typically employs non-invertible neural networks to merge multiple source images into a single fused image.
OUCopula: Bi-Channel Multi-Label Copula-Enhanced Adapter-Based CNN for Myopia Screening Based on OU-UWF Images
Inspired by the complex relationships between OU and the high correlation between the (continuous) outcome labels (Spherical Equivalent and Axial Length), we propose a framework of copula-enhanced adapter convolutional neural network (CNN) learning with OU UWF fundus images (OUCopula) for joint prediction of multiple clinical scores.
Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning
In response to this, inspired by the idea that the functions of the brain are shaped by its geometric structure, this paper integrates this idea into LoRA technology and proposes a new matrix transformation-based reparameterization method for efficient fine-tuning, named Matrix-Transformation based Low-Rank Adaptation (MTLoRA).
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation
Recently, because of the high-quality representations of contrastive learning methods, rehearsal-based contrastive continual learning has been proposed to explore how to continually learn transferable representation embeddings to avoid the catastrophic forgetting issue in traditional continual settings.
Electrical Load Forecasting Model Using Hybrid LSTM Neural Networks with Online Correction
Accurate electrical load forecasting is of great importance for the efficient operation and control of modern power systems.
A Unified Model for Active Battery Equalization Systems
Lithium-ion battery packs demand effective active equalization systems to enhance their usable capacity and lifetime.
Pyramid Feature Attention Network for Monocular Depth Prediction
Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE).
Brain-inspired and Self-based Artificial Intelligence
In this paper, we introduce a Brain-inspired and Self-based Artificial Intelligence (BriSe AI) paradigm.
Enhancing Continuous Domain Adaptation with Multi-Path Transfer Curriculum
Specifically, we construct a transfer curriculum over the source and intermediate domains based on Wasserstein distance, motivated by theoretical analysis of CDA.
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
In this paper, we introduce ChunkAttention, a prefix-aware self-attention module that can detect matching prompt prefixes across multiple requests and share their key/value tensors in memory at runtime to improve the memory utilization of KV cache.
Open Ad Hoc Teamwork with Cooperative Game Theory
Open ad hoc teamwork further complicates this challenge by considering environments with a changing number of teammates, referred to as open teams.
Flexible Physical Camouflage Generation Based on a Differential Approach
This involves incorporating a specially designed adversarial loss and covert constraint loss to guarantee the adversarial and covert nature of the camouflage in the physical world.
Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions
Among existing methods for UTST tasks, attention masking approach and Large Language Models (LLMs) are deemed as two pioneering methods.
Not All Weights Are Created Equal: Enhancing Energy Efficiency in On-Device Streaming Speech Recognition
This study delves into how weight parameters in speech recognition models influence the overall power consumption of these models.
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
The visualization of learning dynamics effectively demonstrates that AgA successfully achieves alignment between individual and collective objectives.
FGeo-HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network
The symbolic part is a formal system built on FormalGeo, which can automatically perform geomertic relational reasoning and algebraic calculations and organize the solving process into a solution hypertree with conditions as hypernodes and theorems as hyperedges.
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences.
Efficient Training Spiking Neural Networks with Parallel Spiking Unit
Efficient parallel computing has become a pivotal element in advancing artificial intelligence.
Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation
The previous methods either failed to accurately fit the face region or lost the interactive generative ability with other existing concepts in T2I models.
BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed.
Activity Detection for Massive Connectivity in Cell-free Networks with Unknown Large-scale Fading, Channel Statistics, Noise Variance, and Activity Probability: A Bayesian Approach
This problem is even more severe in cell-free networks as there are many of these parameters to be acquired.
Localization of Dummy Data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach
Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization.
A New Method for Vehicle Logo Recognition Based on Swin Transformer
Additionally, the use of a transfer learning strategy enables our method to be on par with state-of-the-art VLR methods.
Label-free detection of exosomes from different cellular sources based on surface-enhanced Raman spectroscopy combined with machine learning models
In comparison to other machine learning analysis, our method used small amount of SERS data to allow a simple and rapid exosome detection, which enables a timely subsequent study of cell-cell interactions, communication mechanisms, and disease mechanisms in life sciences.
SCNet: Sparse Compression Network for Music Source Separation
We use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information.
Computation Rate Maximization for Wireless Powered Edge Computing With Multi-User Cooperation
Simulation results show that the performance of the proposed algorithms is comparable to that of the exhaustive search method, and the deep learning-based algorithm significantly reduces the execution time of the algorithm.
Machine Learning Insides OptVerse AI Solver: Design Principles and Applications
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
GloTSFormer: Global Video Text Spotting Transformer
In this paper, we propose a novel Global Video Text Spotting Transformer GloTSFormer to model the tracking problem as global associations and utilize the Gaussian Wasserstein distance to guide the morphological correlation between frames.
Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis
Dynamic community detection methods often lack effective mechanisms to ensure temporal consistency, hindering the analysis of network evolution.
PPBFL: A Privacy Protected Blockchain-based Federated Learning Model
Therefore, we propose A Privacy Protected Blockchain-based Federated Learning Model (PPBFL) to enhance the security of federated learning and encourage active participation of nodes in model training.
DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation
While ensemble models have proven effective, current research in the field of object detection typically focuses on the simple fusion of the outputs of all models, with limited attention being given to developing general adversarial patches that can function effectively in the physical world.
Semantic Draw Engineering for Text-to-Image Creation
Text-to-image generation is conducted through Generative Adversarial Networks (GANs) or transformer models.
PGN: A perturbation generation network against deep reinforcement learning
Deep reinforcement learning has advanced greatly and applied in many areas.
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs
To address this issue, we construct a \textbf{dual relation graph} where each node denotes a relation in the original KG (\textbf{primal entity graph}) and edges are constructed between relations sharing same head or tail entities.
Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, which is crucial to edit the incomplete utterance, and introduce words from irrelevant utterances.
H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer
In this work, we adopt an information theoretic perspective on it and propose a framework named H-ensemble, which dynamically learns the optimal linear combination, or ensemble, of source models for the target task, using a generalization of maximal correlation regression.
Hypergrah-Enhanced Dual Convolutional Network for Bundle Recommendation
While previous approaches have demonstrated notable performance, we argue that they may compromise the ternary relationship among users, items, and bundles.
Rich Human Feedback for Text-to-Image Generation
We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions.
UniAR: Unifying Human Attention and Response Prediction on Visual Content
Such a model would enable predicting subjective feedback such as overall satisfaction or aesthetic quality ratings, along with the underlying human attention or interaction heatmaps and viewing order, enabling designers and content-creation models to optimize their creation for human-centric improvements.
Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning
This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability.
Explainable Trajectory Representation through Dictionary Learning
A hierarchical dictionary learning scheme is also proposed to ensure the algorithm's scalability on large networks, leading to a multi-scale trajectory representation.
Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling
Within the complex neuroarchitecture of the brain, astrocytes play crucial roles in development, structure, and metabolism.
Fine-Grained Extraction of Road Networks via Joint Learning of Connectivity and Segmentation
Road network extraction from satellite images is widely applicated in intelligent traffic management and autonomous driving fields.
Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data
To address this issue, we develop a novel personalized federated learning framework for heterogeneous data, which we refer to as FedSplit.
Resource Allocation for Semantic Communication under Physical-layer Security
The secrecy rate is the communication rate at which no information is disclosed to an eavesdropper.
Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future
With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem.
Perceptual Group Tokenizer: Building Perception with Iterative Grouping
In this paper, we propose the Perceptual Group Tokenizer, a model that entirely relies on grouping operations to extract visual features and perform self-supervised representation learning, where a series of grouping operations are used to iteratively hypothesize the context for pixels or superpixels to refine feature representations.
Ranked #24 on
Self-Supervised Image Classification
on ImageNet
Representation Learning
Self-Supervised Image Classification
+2
Deep Reinforcement Learning Based Optimal Energy Management of Multi-energy Microgrids with Uncertainties
To help EMS formulate optimal dispatching schemes, a deep reinforcement learning (DRL)-based MEMG energy management scheme with renewable energy source (RES) uncertainty is proposed in this paper.
Advancing Attack-Resilient Scheduling of Integrated Energy Systems with Demand Response via Deep Reinforcement Learning
Simulation results demonstrate that our method is capable of adequately addressing the uncertainties resulting from RES and loads, mitigating the impact of cyber-attacks on the scheduling strategy, and ensuring a stable demand supply for various energy sources.
Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS).
FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
Addressing this, we introduce \textsc{FinMem}, a novel LLM-based agent framework devised for financial decision-making.
GENET: Unleashing the Power of Side Information for Recommendation via Hypergraph Pre-training
(2) The diverse semantics of side information that describes items and users from multi-level in a context different from recommendation systems.
FBChain: A Blockchain-based Federated Learning Model with Efficiency and Secure Communication
This article proposes Blockchain-based Federated Learning (FBChain) model for federated learning parameter communication to overcome the above two problems.
Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
This results in a set of candidate answers.
Rethinking and Benchmarking Predict-then-Optimize Paradigm for Combinatorial Optimization Problems
Numerous web applications rely on solving combinatorial optimization problems, such as energy cost-aware scheduling, budget allocation on web advertising, and graph matching on social networks.
CeCNN: Copula-enhanced convolutional neural networks in joint prediction of refraction error and axial length based on ultra-widefield fundus images
Inspired by the spirit that information extracted from the data by statistical methods can improve the prediction accuracy of deep learning models, we formulate a class of multivariate response regression models with a higher-order tensor biomarker, for the bivariate tasks of regression-classification and regression-regression.
In-Context Prompt Editing For Conditional Audio Generation
We show that the framework enhanced the audio quality across the set of collected user prompts, which were edited with reference to the training captions as exemplars.
AdaptMVSNet: Efficient Multi-View Stereo with adaptive convolution and attention fusion
To this end, adaptive convolution is introduced to significantly improve the efficiency in speed and metrics compared to current methods.
FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving
In this paper, we have constructed a consistent formal plane geometry system.
R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context
More analyses and ablation studies show the robustness and generalization of R$^3$ prompting method in solving reasoning tasks in LLMs under noisy context.
ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer's Disease
ADMarker features a novel three-stage multi-modal federated learning architecture that can accurately detect digital biomarkers in a privacy-preserving manner.
BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model
With the increasing importance of machine learning, the privacy and security of training data have become critical.
Kernel Learning in Ridge Regression "Automatically" Yields Exact Low Rank Solution
Assuming that the covariates have nonzero explanatory power for the response only through a low dimensional subspace (central mean subspace), we find that the global minimizer of the finite sample kernel learning objective is also low rank with high probability.
Deep learning based on Transformer architecture for power system short-term voltage stability assessment with class imbalance
This work proposes a Transformer-based STVSA method to address this challenge.
MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks
Consequently, our work complements research on the performance of MLLMs in multimodal comprehension tasks, achieving a more comprehensive and holistic evaluation of MLLMs.
A Zero-Shot Language Agent for Computer Control with Structured Reflection
To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prompting.
Language Models As Semantic Indexers
Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs.
Automatic Macro Mining from Interaction Traces at Scale
Macros are building block tasks of our everyday smartphone activity (e. g., "login", or "booking a flight").
Secondary frequency control of islanded microgrid considering wind and solar stochastics
Finally, a microgrid simulation model including multiple PV and wind DGs is built and performed in various scenarios compared to the traditional secondary frequency control method.
Distribution-free risk assessment of regression-based machine learning algorithms
We solve the risk-assessment problem using the conformal prediction approach, which provides prediction intervals that are guaranteed to contain the true label with a given probability.
Low-carbon optimal dispatch of integrated energy system considering demand response under the tiered carbon trading mechanism
The example results show that considering the carbon trading cost and demand response under the tiered carbon trading mechanism, the total operating cost of IES is reduced by 5. 69% and the carbon emission is reduced by 17. 06%, which significantly improves the reliability, economy and low carbon performance of IES.
Explainable machine learning-based prediction model for diabetic nephropathy
We develop a predictive model by XGB algorithm to screen for DN.
A Demand-Supply Cooperative Responding Strategy in Power System with High Renewable Energy Penetration
In this context, unreasonable profit distributions on the demand-supply side would lead to the conflict of interests and diminish the effectiveness of cooperative responses.
Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
To instantiate this proposal, we design an adaptive rationale guidance network for fake news detection (ARG), in which SLMs selectively acquire insights on news analysis from the LLMs' rationales.
Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection
We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.
For A More Comprehensive Evaluation of 6DoF Object Pose Tracking
The limitations of previous scoring methods and error metrics are analyzed, based on which we introduce our improved evaluation methods.
Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Instead, the bottleneck lies in the linear projection layers of multi-head attention and feedforward networks, constituting a substantial portion of the model size and contributing significantly to computation, memory, and power usage.
Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP
While human prosody annotation contributes a lot to the performance, it is a labor-intensive and time-consuming process, often resulting in inconsistent outcomes.
Maximizing the performance for microcomb based microwave photonic transversal signal processors
Microwave photonic (MWP) transversal signal processors offer a compelling solution for realizing versatile high-speed information processing by combining the advantages of reconfigurable electrical digital signal processing and high-bandwidth photonic processing.
Cross-Utterance Conditioned VAE for Speech Generation
Experimental results on the LibriTTS datasets demonstrate that our proposed models significantly enhance speech synthesis and editing, producing more natural and expressive speech.
TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance
In financial trading contexts, LLMs serve as the decision core for trading agents, leveraging their layered memory system to integrate multi-source historical actions and market insights.
Towards General and Efficient Online Tuning for Spark
The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve high performance.
Short-term power load forecasting method based on CNN-SAEDN-Res
In this method, feature extraction module is composed of a two-dimensional convolutional neural network, which is used to mine the local correlation between data and obtain high-dimensional data features.
Ultrafast-and-Ultralight ConvNet-Based Intelligent Monitoring System for Diagnosing Early-Stage Mpox Anytime and Anywhere
Due to the lack of more efficient diagnostic tools for monkeypox, its spread remains unchecked, presenting a formidable challenge to global health.
Model predictive control strategy in waked wind farms for optimal fatigue loads
In this paper, a closed-loop model predictive controller is developed that minimizes the wind farm tracking errors, the dynamical fatigue load, and and the load equalization.
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.
Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks
This shift in focus from weight adjustment to mastering the intricacies of synaptic change offers a more flexible and dynamic pathway for neural networks to evolve and adapt.
Ear-Keeper: Real-time Diagnosis of Ear Lesions Utilizing Ultralight-Ultrafast ConvNet and Large-scale Ear Endoscopic Dataset
Deep learning-based ear disease diagnosis technology has proven effective and affordable.
Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion
Objective and subjective evaluations show that \textit{Phoneme Hallucinator} outperforms existing VC methods for both intelligibility and speaker similarity.
JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games
This paper presents an empirical exploration of non-transitivity in perfect-information games, specifically focusing on Xiangqi, a traditional Chinese board game comparable in game-tree complexity to chess and shogi.
EEG-based Emotion Style Transfer Network for Cross-dataset Emotion Recognition
The transfer module encodes the domain-specific information of source and target domains and then re-constructs the source domain's emotional pattern and the target domain's statistical characteristics into the new stylized EEG representations.
PMU measurements based short-term voltage stability assessment of power systems via deep transfer learning
Deep learning has emerged as an effective solution for addressing the challenges of short-term voltage stability assessment (STVSA) in power systems.
Contact-conditioned hand-held object reconstruction from single-view images
Reconstructing the shape of hand-held objects from single-view color images is a long-standing problem in computer vision and computer graphics.
InvVis: Large-Scale Data Embedding for Invertible Visualization
We propose a new method to efficiently express chart data in the form of images, enabling large-capacity data embedding.
CeRF: Convolutional Neural Radiance Fields for New View Synthesis with Derivatives of Ray Modeling
In recent years, novel view synthesis has gained popularity in generating high-fidelity images.
A large calcium-imaging dataset reveals a systematic V4 organization for natural scenes
To gain deeper insights into visual processing of natural scenes, we utilized widefield calcium-imaging of primate V4 in response to many natural images, generating a large dataset of columnar-scale responses.
InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs
Inspired by the philosophy of ``think-like-a-vertex", a GAS-like (Gather-Apply-Scatter) schema is proposed to describe the computation paradigm and data flow of GNN inference.
Farthest Streamline Sampling for the Uniform Distribution of Forearm Muscle Fiber Tracts from Diffusion Tensor Imaging
FSS reduced the sampling of long tracts (10% reduction in fiber length, P<0. 05), and the architectural parameters were within physiological ranges (two parameters with P<0. 05).
Recent Developments in Recommender Systems: A Survey
The objective of this study is to provide an overview of the current state-of-the-art in the field and highlight the latest trends in the development of recommender systems.
Computing large deviation prefactors of stochastic dynamical systems based on machine learning
In this paper, we present large deviation theory that characterizes the exponential estimate for rare events of stochastic dynamical systems in the limit of weak noise.
Collaborative Optimization of Multi-microgrids System with Shared Energy Storage Based on Multi-agent Stochastic Game and Reinforcement Learning
The proposed MMG system framework can reduce energy fluctuations in the main grid by 1746. 5kW in 24 hours and achieve a cost reduction of 16. 21% in the test.
FewSAR: A Few-shot SAR Image Classification Benchmark
Motivated by this observation, we propose a novel few-shot SAR image classification benchmark (FewSAR) to address this issue.
Output Voltage Response Improvement and Ripple Reduction Control for Input-parallel Output-parallel High-Power DC Supply
A three-phase isolated AC-DC-DC power supply is widely used in the industrial field due to its attractive features such as high-power density, modularity for easy expansion and electrical isolation.
History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
Context information modeling is an important task in conversational KBQA.
Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination
In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy.
Image encryption for Offshore wind power based on 2D-LCLM and Zhou Yi Eight Trigrams
In this paper, we propose a new encryption algorithm for offshore wind power based on two-dimensional lagged complex logistic mapping (2D-LCLM) and Zhou Yi Eight Trigrams.
PaLI-X: On Scaling up a Multilingual Vision and Language Model
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture.
Ranked #1 on
Fine-Grained Image Recognition
on OVEN
Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistency
Notably, our algorithm has achieved state-of-the-art performance on neuromorphic datasets DVS-CIFAR10 and N-Caltech101, and can achieve superior performance in the test phase with timestep T=1.
Dive into the Power of Neuronal Heterogeneity
The biological neural network is a vast and diverse structure with high neural heterogeneity.
Feature Chirality in Deep Learning Models
As deep learning applications extensively increase by leaps and bounds, their interpretability has become increasingly prominent.
A Sea-Land Clutter Classification Framework for Over-the-Horizon-Radar Based on Weighted Loss Semi-supervised GAN
The semi-supervised classification performance of WL-SSGAN is evaluated on a sea-land clutter dataset.
MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer
With the increasing demand for video understanding, video moment and highlight detection (MHD) has emerged as a critical research topic.
MINN: Learning the dynamics of differential-algebraic equations and application to battery modeling
The concept of integrating physics-based and data-driven approaches has become popular for modeling sustainable energy systems.
OpenBox: A Python Toolkit for Generalized Black-box Optimization
Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, experimental design, and database knob tuning.
Binary stochasticity enabled highly efficient neuromorphic deep learning achieves better-than-software accuracy
We propose a binary stochastic learning algorithm that modifies all elementary neural network operations, by introducing (i) stochastic binarization of both the forwarding signals and the activation function derivatives, (ii) signed binarization of the backpropagating errors, and (iii) step-wised weight updates.
OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments.
Graph-based Topology Reasoning for Driving Scenes
Understanding the road genome is essential to realize autonomous driving.
Ranked #5 on
3D Lane Detection
on OpenLane-V2 val
Multi-Microgrid Collaborative Optimization Scheduling Using an Improved Multi-Agent Soft Actor-Critic Algorithm
The implementation of a multi-microgrid (MMG) system with multiple renewable energy sources enables the facilitation of electricity trading.
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X
Large pre-trained code generation models, such as OpenAI Codex, can generate syntax- and function-correct code, making the coding of programmers more productive and our pursuit of artificial general intelligence closer.
Ranked #81 on
Code Generation
on MBPP
MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networks
The self-adaptation to membrane potential and input allows a timely adjustment of the threshold to fire spike faster and transmit more information.
An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain
In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data.
Ensemble Nonlinear Model Predictive Control for Residential Solar-Battery Energy Management
In a dynamic distribution market environment, residential prosumers with solar power generation and battery energy storage devices can flexibly interact with the power grid via power exchange.
Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
With the help of the Internet and communication terminal, Mpox-AISM can perform a real-time, low-cost, and convenient diagnosis for earlier-stage mpox in various real-world settings, thereby effectively curbing the spread of mpox virus.
Multi-Task Sub-Band Network For Deep Residual Echo Suppression
This paper introduces the SWANT team entry to the ICASSP 2023 AEC Challenge.
A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning
To tune different components for DBMS, a coordinating mechanism is needed to make the multiple agents cognizant of each other.
Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networks
Instead, we propose two methods to improve the representational power of AGCs by utilizing 1) structural information in a high-dimensional space and 2) multiple attention functions when calculating their weights.
Transfer Learning for Bayesian Optimization: A Survey
A wide spectrum of design and decision problems, including parameter tuning, A/B testing and drug design, intrinsically are instances of black-box optimization.
Cooperative Open-ended Learning Framework for Zero-shot Coordination
However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility.
Rover: An online Spark SQL tuning service via generalized transfer learning
When applying transfer learning to accelerate the tuning process, we notice two domain-specific challenges: 1) most previous work focus on transferring tuning history, while expert knowledge from Spark engineers is of great potential to improve the tuning performance but is not well studied so far; 2) history tasks should be carefully utilized, where using dissimilar ones lead to a deteriorated performance in production.
DivBO: Diversity-aware CASH for Ensemble Learning
To tackle this issue and further enhance the ensemble performance, we propose DivBO, a diversity-aware framework to inject explicit search of diversity into the CASH problems.
HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline
On top of the observations that industrial formulae exhibit clear community structure and oversplit substructures lead to the difficulty in semantic formation of logical structures, we propose HardSATGEN, which introduces a fine-grained control mechanism to the neural split-merge paradigm for SAT formula generation to better recover the structural and computational properties of the industrial benchmarks.
PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
Layout design is an important task in various design fields, including user interface, document, and graphic design.
GPU-based Private Information Retrieval for On-Device Machine Learning Inference
Together, for various on-device ML applications such as recommendation and language modeling, our system on a single V100 GPU can serve up to $100, 000$ queries per second -- a $>100 \times$ throughput improvement over a CPU-based baseline -- while maintaining model accuracy.
Data-Driven Distributionally Robust Scheduling of Community Integrated Energy Systems with Uncertain Renewable Generations Considering Integrated Demand Response
A community integrated energy system (CIES) is an important carrier of the energy internet and smart city in geographical and functional terms.
HTTE: A Hybrid Technique For Travel Time Estimation In Sparse Data Environments
Travel time estimation is a critical task, useful to many urban applications at the individual citizen and the stakeholder level.
Finding the Most Transferable Tasks for Brain Image Segmentation
Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance.
INT2: Interactive Trajectory Prediction at Intersections
One of the most challenging problems in motion forecasting is interactive trajectory prediction, whose goal is to jointly forecasts the future trajectories of interacting agents.
SparseMAE: Sparse Training Meets Masked Autoencoders
In this paper, we aim to reduce model complexity from large vision transformers pretrained by MAE with assistant of sparse training.
Federated Multi-Agent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multi-Microgrid Energy Management
Then, these local models are periodically uploaded to a server and their parameters are aggregated to build a global agent, which will be broadcasted to MGs and replace their local agents.
Optimal scheduling of island integrated energy systems considering multi-uncertainties and hydrothermal simultaneous transmission: A deep reinforcement learning approach
Multi-uncertainties from power sources and loads have brought significant challenges to the stable demand supply of various resources at islands.
An Information-Theoretic Approach to Transferability in Task Transfer Learning
Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks.
ENGNN: A General Edge-Update Empowered GNN Architecture for Radio Resource Management in Wireless Networks
In order to achieve high data rate and ubiquitous connectivity in future wireless networks, a key task is to efficiently manage the radio resource by judicious beamforming and power allocation.
Super-resolution Probabilistic Rain Prediction from Satellite Data Using 3D U-Nets and EarthFormers
To further improve the model performance, multi-model ensemble and threshold optimization were used to produce the final probabilistic rain prediction.
A Dual-scale Lead-seperated Transformer With Lead-orthogonal Attention And Meta-information For Ecg Classification
Auxiliary diagnosis of cardiac electrophysiological status can be obtained through the analysis of 12-lead electrocardiograms (ECGs).
Learning Cooperative Beamforming with Edge-Update Empowered Graph Neural Networks
However, the current GNNs are only equipped with the node-update mechanism, which restricts it from modeling more complicated problems such as the cooperative beamforming design, where the beamformers are on the graph edges of wireless networks.
Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams
The first solution Vanilla is to perform self-training, augmenting the supervised training data with predicted pseudo-labeled instances of the current task, while replacing the full volume retraining with episodic memory replay to balance the training efficiency with the performance of previous tasks.
Hierarchical Estimation for Effective and Efficient Sampling Graph Neural Network
On account that previous studies either lacks variance analysis or only focus on a particular sampling paradigm, we firstly propose an unified node sampling variance analysis framework and analyze the core challenge "circular dependency" for deriving the minimum variance sampler, i. e., sampling probability depends on node embeddings while node embeddings can not be calculated until sampling is finished.
Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence
We compare the prediction performance for different intelligence measures based on static FC, dynamic FC, and region level time series acquired from the Adolescent Brain Cognitive Development (ABCD) study involving close to 7000 individuals.
CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification
Basically, an instance-dependent soft prefix, derived from fact-counterfactual pairs in the label space, is leveraged to complement the language verbalizers in many-class classification.
A Random Forest and Current Fault Texture Feature-Based Method for Current Sensor Fault Diagnosis in Three-Phase PWM VSR
The current sensor faults may bring hidden danger or damage to the whole system; therefore, this paper proposed a random forest (RF) and current fault texture feature-based method for current sensor fault diagnosis in three-phase PWM VSR systems.
Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach
To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL).
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers
We show how factoring the RNN-T's output distribution can significantly reduce the computation cost and power consumption for on-device ASR inference with no loss in accuracy.
Review on Monitoring, Operation and Maintenance of Smart Offshore Wind Farms
In recent years, with the development of wind energy, the number and scale of wind farms are developing rapidly.
GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs
However, it remains challenging to model the negation and union operator.
Self-supervised Graph-based Point-of-interest Recommendation
In order to counteract the scarcity and incompleteness of POI check-ins, we propose a novel self-supervised learning paradigm in \ssgrec, where the trajectory representations are contrastively learned from two augmented views on geolocations and temporal transitions.
Understanding Embodied Reference with Touch-Line Transformer
Human studies have revealed that objects referred to or pointed to do not lie on the elbow-wrist line, a common misconception; instead, they lie on the so-called virtual touch line.
Contrastive Bayesian Analysis for Deep Metric Learning
Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other.
Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus
Specifically, we enhance a vision-language model that only takes the screenshot of the UI and a region of interest on the screen -- the focus -- as the input.
MUG: Interactive Multimodal Grounding on User Interfaces
To investigate the problem, we create a new dataset that consists of 77, 820 sequences of human user-agent interaction on mobile interfaces in which 20% involves multiple rounds of interactions.
Controlling mean exit time of stochastic dynamical systems based on quasipotential and machine learning
The mean exit time escaping basin of attraction in the presence of white noise is of practical importance in various scientific fields.
Optimal dispatch of low-carbon integrated energy system considering nuclear heating and carbon trading
The development of miniaturized nuclear power (NP) units and the improvement of the carbon trading market provide a new way to realize the low-carbon operation of integrated energy systems (IES).
IRS Assisted NOMA Aided Mobile Edge Computing with Queue Stability: Heterogeneous Multi-Agent Reinforcement Learning
In this paper, we investigate the joint offloading, communication and computation resource allocation for IRS-assisted NOMA MEC system.
Enabling Conversational Interaction with Mobile UI using Large Language Models
This paper investigates the feasibility of enabling versatile conversational interactions with mobile UIs using a single LLM.
SDFE-LV: A Large-Scale, Multi-Source, and Unconstrained Database for Spotting Dynamic Facial Expressions in Long Videos
In this paper, we present a large-scale, multi-source, and unconstrained database called SDFE-LV for spotting the onset and offset frames of a complete dynamic facial expression from long videos, which is known as the topic of dynamic facial expression spotting (DFES) and a vital prior step for lots of facial expression analysis tasks.
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
To the best of our knowledge, this is the first study for objective DDH diagnosis by leveraging deep learning keypoint detection and integrating different anatomical measurements, which can provide reliable and explainable support for clinical decision-making.
Video-based Cross-modal Auxiliary Network for Multimodal Sentiment Analysis
Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions.
Distance-Aware Occlusion Detection with Focused Attention
In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection.
Human-Object Interaction Detection
Relationship Detection
+1
Resilience assessment and improvement for electric power transmission systems against typhoon disasters: A data-model hybrid driven approach
In response to the damage to electric power transmission systems caused by typhoon disasters in coastal areas, a planning-targeted resilience assessment framework that considers the impact of multiple factors is established to accurately find the weak links of the transmission system and improve the system resilience.
GraphTTA: Test Time Adaptation on Graph Neural Networks
In this paper, we present a novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data.
Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment
In this work, we guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process.
A Real-time Edge-AI System for Reef Surveys
Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels.
A Universal PINNs Method for Solving Partial Differential Equations with a Point Source
In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs)method emerges to be a promising method for solving both forward and inverse PDE problems.
BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation
These brain-inspired AI models have been effectively validated on various supervised, unsupervised, and reinforcement learning tasks, and they can be used to enable AI models to be with multiple brain-inspired cognitive functions.
Transferability-Guided Cross-Domain Cross-Task Transfer Learning
We propose two novel transferability metrics F-OTCE (Fast Optimal Transport based Conditional Entropy) and JC-OTCE (Joint Correspondence OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more transferable representations for cross-domain cross-task transfer learning.
Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge
Domain generalization aims at learning a universal model that performs well on unseen target domains, incorporating knowledge from multiple source domains.
An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections
By integrating the above three adaptive mechanisms and STB-STDP, our model greatly accelerates the training of unsupervised spiking neural networks and improves the performance of unsupervised SNNs on complex tasks.
Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation
Spiking neural network (SNN) has been attached to great importance due to the properties of high biological plausibility and low energy consumption on neuromorphic hardware.
Auto-Encoder-Extreme Learning Machine Model for Boiler NOx Emission Concentration Prediction
An automatic encoder (AE) extreme learning machine (ELM)-AE-ELM model is proposed to predict the NOx emission concentration based on the combination of mutual information algorithm (MI), AE, and ELM.
Warped Convolutional Networks: Bridge Homography to sl(3) algebra by Group Convolution
In this paper, we propose Warped Convolution Networks (WCN) to effectively learn and represent the homography by SL(3) group and sl(3) algebra with group convolution.
Efficient End-to-End AutoML via Scalable Search Space Decomposition
End-to-end AutoML has attracted intensive interests from both academia and industry which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning.
DFG-NAS: Deep and Flexible Graph Neural Architecture Search
Graph neural networks (GNNs) have been intensively applied to various graph-based applications.
NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning
First, GNNs can learn higher-order structural information by stacking more layers but can not deal with large depth due to the over-smoothing issue.
Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design.
Graph Attention Multi-Layer Perceptron
Graph neural networks (GNNs) have achieved great success in many graph-based applications.
Ranked #11 on
Node Property Prediction
on ogbn-mag
Solving the Spike Feature Information Vanishing Problem in Spiking Deep Q Network with Potential Based Normalization
Brain inspired spiking neural networks (SNNs) have been successfully applied to many pattern recognition domains.
Transfer Learning based Search Space Design for Hyperparameter Tuning
The extensive experiments show that our approach considerably boosts BO by designing a promising and compact search space instead of using the entire space, and outperforms the state-of-the-arts on a wide range of benchmarks, including machine learning and deep learning tuning tasks, and neural architecture search.
TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning
With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important.
