Search Results for author:
Found 101 papers, 28 papers with code
Adaptive Wall-Following Control for Unmanned Ground Vehicles Using Spiking Neural Networks
Unmanned ground vehicles operating in complex environments must adaptively adjust to modeling uncertainties and external disturbances to perform tasks such as wall following and obstacle avoidance.
AdaGC: Improving Training Stability for Large Language Model Pretraining
Large Language Models (LLMs) face increasing loss spikes during scaling, undermining training stability and final performance.
Breaking Memory Limits: Gradient Wavelet Transform Enhances LLMs Training
Large language models (LLMs) have shown impressive performance across a range of natural language processing tasks.
Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
However, SAM employs a fixed hyperparameter associated with the regularization to characterize the sharpness of the model.
Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities
The first stage, AI for Network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences.
Bundle Choice Model with Endogenous Regressors: An Application to Soda Tax
This paper proposes a Bayesian factor-augmented bundle choice model to estimate joint consumption as well as the substitutability and complementarity of multiple goods in the presence of endogenous regressors.
FullStack Bench: Evaluating LLMs as Full Stack Coders
As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing.
Average-Over-Time Spiking Neural Networks for Uncertainty Estimation in Regression
However, efficient uncertainty estimation methods for spiking neural networks, particularly for regression models, have been lacking.
Deep learning-based spatio-temporal fusion for high-fidelity ultra-high-speed x-ray radiography
In this paper, we investigate the use of a deep learning-based spatio-temporal fusion (STF) framework to fuse two complementary sequences of x-ray images and reconstruct the target image sequence with high spatial resolution, high frame rate, and high fidelity.
Graph Transformer Networks for Accurate Band Structure Prediction: An End-to-End Approach
Here, we introduce a graph Transformer-based end-to-end approach that directly predicts band structures from crystal structures with high accuracy.
MdEval: Massively Multilingual Code Debugging
Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet.
Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise
This paper investigates the roles of gradient normalization and clipping in ensuring the convergence of Stochastic Gradient Descent (SGD) under heavy-tailed noise.
Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models
To align the learning process across multiple views, we utilize GPS trajectories as a bridge and employ self-supervised pretext tasks to capture and distinguish movement patterns across different spatial views.
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations
Through simultaneous optimization of the backdoored model and trigger generator, guided by dynamic data augmentation operation selectors, we achieve significant advancements.
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
This dataset is easily integrated with existing direct alignment algorithms and is applicable to any preference dataset.
Backdooring Vision-Language Models with Out-Of-Distribution Data
The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs.
BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data
BabelBench incorporates a dataset comprising 247 meticulously curated problems that challenge the models with tasks in perception, commonsense reasoning, logical reasoning, and so on.
Federated Prediction-Powered Inference from Decentralized Data
The Fed-PPI framework involves training local models on private data, aggregating them through Federated Learning (FL), and deriving confidence intervals using PPI computation.
DPSNN: Spiking Neural Network for Low-Latency Streaming Speech Enhancement
Inspired by Dual-Path Spiking Neural Networks (DPSNNs) in classical neural networks, we develop a two-phase time-domain streaming SNN framework -- the Dual-Path Spiking Neural Network (DPSNN).
Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations
This paper provides a comprehensive generalization analysis of three representative STORM-based algorithms: STORM, COVER, and SVMR, for one, two, and $K$-level stochastic optimizations under both convex and strongly convex settings based on algorithmic stability.
UniCoder: Scaling Code Large Language Model via Universal Code
When applying LLMs for code generation, recent works mainly focus on directing the models to articulate intermediate natural-language reasoning steps, as in chain-of-thought (CoT) prompting, and then output code with the natural language or other structured intermediate steps.
FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering
Retrieval Augmented Generation (RAG) has become prevalent in question-answering (QA) tasks due to its ability of utilizing search engine to enhance the quality of long-form question-answering (LFQA).
Brain-Inspired Spike Echo State Network Dynamics for Aero-Engine Intelligent Fault Prediction
Aero-engine fault prediction aims to accurately predict the development trend of the future state of aero-engines, so as to diagnose faults in advance.
XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser
In the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task.
Score-based Generative Models with Adaptive Momentum
Score-based generative models have demonstrated significant practical success in data-generating tasks.
1st Place Solution to the 1st SkatingVerse Challenge
This paper presents the winning solution for the 1st SkatingVerse Challenge.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
A Survey of Reasoning for Substitution Relationships: Definitions, Methods, and Directions
Substitute relationships are fundamental to people's daily lives across various domains.
Accelerating Federated Learning by Selecting Beneficial Herd of Local Gradients
Federated Learning (FL) is a distributed machine learning framework in communication network systems.
RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning
Recent advancements in Large Language Models (LLMs) and Large Multi-modal Models (LMMs) have shown potential in various medical applications, such as Intelligent Medical Diagnosis.
REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models
Leveraging clinical notes and multivariate time-series EHR, existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge, particularly from the knowledge graph (KG).
OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy
We advance the field of Parameter-Efficient Fine-Tuning (PEFT) with our novel multi-adapter method, OrchMoE, which capitalizes on modular skill architecture for enhanced forward transfer in neural networks.
SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor
In this work, we propose a VIsion Permutable extractor for fast and efficient Scene Text Recognition (SVIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR.
GACE: Learning Graph-Based Cross-Page Ads Embedding For Click-Through Rate Prediction
In this paper, we proposed GACE, a graph-based cross-page ads embedding generation method.
xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.
Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
Modular and composable transfer learning is an emerging direction in the field of Parameter Efficient Fine-Tuning, as it enables neural networks to better organize various aspects of knowledge, leading to improved cross-task generalization.
Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change
To this end, we introduce the Nothing Stands Still (NSS) benchmark, which focuses on the spatiotemporal registration of 3D scenes undergoing large spatial and temporal change, ultimately creating one coherent spatiotemporal map.
Rethinking SIGN Training: Provable Nonconvex Acceleration without First- and Second-Order Gradient Lipschitz
Sign-based stochastic methods have gained attention due to their ability to achieve robust performance despite using only the sign information for parameter updates.
Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis
Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently.
$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
Despite policy-based RL methods dominating the literature on RL for program synthesis, the nature of program synthesis tasks hints at a natural alignment with value-based methods.
Stability and Generalization for Minibatch SGD and Local SGD
We show both minibatch and local SGD achieve a linear speedup to attain the optimal risk bounds.
Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent
Stochastic gradient descent (SGD) performed in an asynchronous manner plays a crucial role in training large-scale machine learning models.
MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimation
The object pose predictor then generates canonical object representations from RGB images.
DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction
Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making.
Temporal Contrastive Learning for Spiking Neural Networks
However, in this work, we find the method above is not ideal for the SNNs training as it omits the temporal dynamics of SNNs and degrades the performance quickly with the decrease of inference time steps.
Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Model
JPD of MRI and noise-added PET was learned in the diffusion process.
Efficient Uncertainty Estimation in Spiking Neural Networks via MC-dropout
Spiking neural networks (SNNs) have gained attention as models of sparse and event-driven communication of biological neurons, and as such have shown increasing promise for energy-efficient applications in neuromorphic hardware.
NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems
To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems.
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
It detects possible triggers in the token space using image structural similarity and label consistency between the test image and MAE restorations.
Hybrid Spiking Neural Network Fine-tuning for Hippocampus Segmentation
Over the past decade, artificial neural networks (ANNs) have made tremendous advances, in part due to the increased availability of annotated data.
Towards Vision Transformer Unrolling Fixed-Point Algorithm: a Case Study on Image Restoration
It provides a promising way to introduce the Transformer in low-level vision tasks.
Backdoor Cleansing with Unlabeled Data
In experiments, we show that our method, trained without labels, is on-par with state-of-the-art defense methods trained using labels.
Individualized Conditioning and Negative Distances for Speaker Separation
Speaker separation aims to extract multiple voices from a mixed signal.
Domain Adaptation with Adversarial Training on Penultimate Activations
We show that this strategy is more efficient and better correlated with the objective of boosting prediction confidence than adversarial training on input images or intermediate features, as used in previous works.
Local Context-Aware Active Domain Adaptation
In this paper, we propose a Local context-aware ADA framework, named LADA, to address this issue.
Adaptive and Implicit Regularization for Matrix Completion
Theoretically, we show that the adaptive regularization of \ReTwo{AIR} enhances the implicit regularization and vanishes at the end of training.
Prior Knowledge Guided Unsupervised Domain Adaptation
We propose a general rectification module that uses such prior knowledge to refine model generated pseudo labels.
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems.
Spotlights: Probing Shapes from Spherical Viewpoints
Recent years have witnessed the surge of learned representations that directly build upon point clouds.
S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization
In the GNN query module, the pose graph is transformed to form a embedding-aggregated reference graph for camera relocalization.
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast
We present an approach to learn voice-face representations from the talking face videos, without any identity labels.
Safe Self-Refinement for Transformer-based Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain.
Ranked #4 on
Domain Adaptation
on Office-31
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
In this paper, to eliminate the effort for tuning the momentum-related hyperparameter, we propose a new adaptive momentum inspired by the optimal choice of the heavy ball momentum for quadratic optimization.
AIR-Net: Adaptive and Implicit Regularization Neural Network for Matrix Completion
Theoretically, we show that the adaptive regularization of AIR enhances the implicit regularization and vanishes at the end of training.
Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications
Many critical applications rely on cameras to capture video footage for analytical purposes.
On the Practicality of Deterministic Epistemic Uncertainty
We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.
Out of Distribution (OOD) Detection
Semantic Segmentation
+1
Decentralized Federated Averaging
In FedAvg, clients keep their data locally for privacy protection; a central parameter server is used to communicate between clients.
Stability and Generalization of the Decentralized Stochastic Gradient Descent
The stability and generalization of stochastic gradient-based methods provide valuable insights into understanding the algorithmic performance of machine learning models.
Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
In recent years, the Deep Learning Alternating Minimization (DLAM), which is actually the alternating minimization applied to the penalty form of the deep neutral networks training, has been developed as an alternative algorithm to overcome several drawbacks of Stochastic Gradient Descent (SGD) algorithms.
Three-quarter Sibling Regression for Denoising Observational Data
However, it will remove intrinsic variability if the variables are dependent, and therefore does not apply to many situations, including modeling of species counts that are controlled by common causes.
Robust Multi-Agent Reinforcement Learning with Model Uncertainty
In contrast, we model the problem as a robust Markov game, where the goal of all agents is to find policies such that no agent has the incentive to deviate, i. e., reach some equilibrium point, which is also robust to the possible uncertainty of the MARL model.
REPAINT: Knowledge Transfer in Deep Reinforcement Learning
Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low.
REPAINT: Knowledge Transfer in Deep Actor-Critic Reinforcement Learning
Accelerating the learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low or unknown.
End-to-end Full Projector Compensation
Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface.
FedGAN: Federated Generative Adversarial Networks for Distributed Data
We propose Federated Generative Adversarial Network (FedGAN) for training a GAN across distributed sources of non-independent-and-identically-distributed data sources subject to communication and privacy constraints.
Adaptive Temporal Difference Learning with Linear Function Approximation
Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes.
Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks
Simulation-to-simulation and simulation-to-real world transfer of neural network models have been a difficult problem.
DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning
DeepRacer is a platform for end-to-end experimentation with RL and can be used to systematically investigate the key challenges in developing intelligent control systems.
General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme
In this paper, we propose a general proximal incremental aggregated gradient algorithm, which contains various existing algorithms including the basic incremental aggregated gradient method.
Decentralized Markov Chain Gradient Descent
Decentralized stochastic gradient method emerges as a promising solution for solving large-scale machine learning problems.
Coexistence under hierarchical resource exploitation: the role of R*-preemption tradeoff
Thus, we developed an extension of resource competition theory to investigate partial and total preemption (in the latter, the preemptor is unaffected by species with lower preemption rank).
Inertial nonconvex alternating minimizations for the image deblurring
In image processing, Total Variation (TV) regularization models are commonly used to recover blurred images.
Heavy-ball Algorithms Always Escape Saddle Points
In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points?
Leveraging Crowdsourced GPS Data for Road Extraction from Aerial Imagery
Deep learning is revolutionizing the mapping industry.
Ranked #5 on
Semantic Segmentation
on Porto
Trace-back along capsules and its application on semantic segmentation
In this paper, we propose a capsule-based neural network model to solve the semantic segmentation problem.
phq: a Fortran code to compute phonon quasiparticle properties and dispersions
We here introduce a Fortran code that computes anharmonic free energy of solids from first-principles based on our phonon quasiparticle approach.
Materials Science
Iteratively reweighted penalty alternating minimization methods with continuation for image deblurring
In this paper, we consider a class of nonconvex problems with linear constraints appearing frequently in the area of image processing.
TraceCaps: A Capsule-based Neural Network for Semantic Segmentation
We model this procedure as a traceback pipeline and take it as a central piece to build an end-to-end segmentation network.
Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning
In this paper, we propose an efficient quality-aware deep neural network to model the weight of data from each domain using deep reinforcement learning (DRL).
Markov Chain Block Coordinate Descent
random and cyclic selections are either infeasible or very expensive.
Non-ergodic Convergence Analysis of Heavy-Ball Algorithms
For objective functions satisfying a relaxed strongly convex condition, the linear convergence is established under weaker assumptions on the step size and inertial parameter than made in the existing literature.
On Markov Chain Gradient Descent
This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the trajectory of a Markov chain.
An Efficient ADMM-Based Algorithm to Nonconvex Penalized Support Vector Machines
Support vector machines (SVMs) with sparsity-inducing nonconvex penalties have received considerable attentions for the characteristics of automatic classification and variable selection.
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning
This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation.
Non-ergodic Complexity of Convex Proximal Inertial Gradient Descents
The non-ergodic O(1/k) rate is proved for proximal inertial gradient descent with constant stepzise when the objective function is coercive.
A convergence framework for inexact nonconvex and nonsmooth algorithms and its applications to several iterations
In fact, a lot of classical inexact nonconvex and nonsmooth algorithms allow these three conditions.
Iteratively Linearized Reweighted Alternating Direction Method of Multipliers for a Class of Nonconvex Problems
The traditional alternating direction method of multipliers encounters troubles in both mathematics and computations in solving the nonconvex and nonsmooth subproblem.
Differentially Private Learning of Graphical Models using CGMs
A naive learning algorithm that uses the noisy sufficient statistics “as is” outperforms general-purpose differentially private learning algorithms.
Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models
We investigate the problem of learning discrete, undirected graphical models in a differentially private way.
