Search Results for author:
Found 69 papers, 35 papers with code
Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing
Unsupervised cross-domain dependency parsing is to accomplish domain adaptation for dependency parsing without using labeled data in target domain.
Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
In this study, we propose a training-free projection-based continual merging method that processes models sequentially through orthogonal projections of weight matrices and adaptive scaling mechanisms.
Leveraging Metamemory Mechanisms for Enhanced Data-Free Code Generation in LLMs
Automated code generation using large language models (LLMs) has gained attention due to its efficiency and adaptability.
MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification
To remedy these drawbacks, we propose a novel HSI classification model based on a Mamba model, named MambaHSI, which can simultaneously model long-range interaction of the whole image and integrate spatial and spectral information in an adaptive manner.
Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Experimental results demonstrate that SDPO consistently outperforms prior methods in reward-based alignment across diverse step configurations, underscoring its robust step generalization capabilities.
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
Building on WEMoE, we further introduce an efficient-and-effective WEMoE (E-WEMoE) method, whose core mechanism involves eliminating non-essential elements in the critical modules of WEMoE and implementing shared routing across multiple MoE modules, thereby significantly reducing both the trainable parameters, the overall parameter count, and computational overhead of the merged model by WEMoE.
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
To bridge this gap, we propose ADEM-VL, an efficient vision-language method that tunes VL models based on pretrained large language models (LLMs) by adopting a parameter-free cross-attention mechanism for similarity measurements in multimodal fusion.
MG-Net: Learn to Customize QAOA with Circuit Depth Awareness
To address this dilemma, here we first analyze the convergence behavior of QAOA, uncovering the origins of this dilemma and elucidating the intricate relationship between the employed mixer Hamiltonian, the specific problem at hand, and the permissible maximum circuit depth.
$\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding
Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt.
Joint Input and Output Coordination for Class-Incremental Learning
This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks.
Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models
Building upon this insight, we propose Divide, Conquer and Combine (DC$^2$), a novel training-free framework for enhancing MLLM perception of HR images.
Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets
In a real federated learning (FL) system, communication overhead for passing model parameters between the clients and the parameter server (PS) is often a bottleneck.
SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models
Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models.
Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion
Once the routers are learned and a preference vector is set, the MoE module can be unloaded, thus no additional computational cost is introduced during inference.
FusionBench: A Comprehensive Benchmark of Deep Model Fusion
These techniques range from model ensemble methods, which combine the predictions to improve the overall performance, to model merging, which integrates different models into a single one, and model mixing methods, which upscale or recombine the components of the original models.
Separable Power of Classical and Quantum Learning Protocols Through the Lens of No-Free-Lunch Theorem
The No-Free-Lunch (NFL) theorem, which quantifies problem- and data-independent generalization errors regardless of the optimization process, provides a foundational framework for comprehending diverse learning protocols' potential.
Federated Learning with Only Positive Labels by Exploring Label Correlations
Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading
Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated.
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Then, we surprisingly discover that dormant neurons in our critic model act as a regularization against reward overoptimization while active neurons reflect primacy bias.
Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
A notable challenge is mitigating the interference between parameters of different models, which can substantially deteriorate performance.
WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge
Sentiment analysis is rapidly advancing by utilizing various data modalities (e. g., text, image).
OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models
Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e. g., HumanEval and MBPP.
Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names
This motivates us to study GZSL in the more practical setting where unseen classes can be either similar or dissimilar to seen classes.
Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion
At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model.
Learn From Model Beyond Fine-Tuning: A Survey
LFM focuses on the research, modification, and design of FM based on the model interface, so as to better understand the model structure and weights (in a black box environment), and to generalize the model to downstream tasks.
Parameter Efficient Multi-task Model Fusion with Partial Linearization
We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model, outperforming standard adapter tuning and task arithmetic alone.
Zero-shot Learning of Drug Response Prediction for Preclinical Drug Screening
In this paper, we propose a zero-shot learning solution for the DRP task in preclinical drug screening.
Ranked #1 on
Zero-Shot Learning
on GDSCv2
Decompose Semantic Shifts for Composed Image Retrieval
Composed image retrieval is a type of image retrieval task where the user provides a reference image as a starting point and specifies a text on how to shift from the starting point to the desired target image.
DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices
Our objective is to achieve fast and energy-efficient collaborative inference while maintaining comparable accuracy compared with large ViTs.
PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
In this work, we address the task of few-shot part segmentation, which aims to segment the different parts of an unseen object using very few labeled examples.
Rethinking the Localization in Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision.
LGViT: Dynamic Early Exiting for Accelerating Vision Transformer
Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks.
Multi-Granularity Hand Action Detection
To fill this gap, we introduce the FHA-Kitchens (Fine-Grained Hand Actions in Kitchen Scenes) dataset, providing both coarse- and fine-grained hand action categories along with localization annotations.
Transition Role of Entangled Data in Quantum Machine Learning
Recent progress has highlighted its positive impact on learning quantum dynamics, wherein the integration of entanglement into quantum operations or measurements of quantum machine learning (QML) models leads to substantial reductions in training data size, surpassing a specified prediction error threshold.
Improving Heterogeneous Model Reuse by Density Estimation
This paper studies multiparty learning, aiming to learn a model using the private data of different participants.
Unsupervised Cross-domain Pulmonary Nodule Detection without Source Data
Cross-domain pulmonary nodule detection suffers from performance degradation due to a large shift of data distributions between the source and target domain.
SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention
To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks.
FedABC: Targeting Fair Competition in Personalized Federated Learning
In particular, we adopt the ``one-vs-all'' training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class.
MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs
The vision of this paper is to provide a more comprehensive and practical benchmark study for MIG in order to eliminate the need for tedious manual benchmarking and tuning efforts.
Depression Diagnosis and Analysis via Multimodal Multi-order Factor Fusion
Multimodal learning is a popular solution for automatic diagnosis of depression, and the existing works suffer two main drawbacks: 1) the high-order interactions between different modalities can not be well exploited; and 2) interpretability of the models are weak.
Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition
To address the above issues, we propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition.
Symmetric Pruning in Quantum Neural Networks
To fill this knowledge gap, here we propose the effective quantum neural tangent kernel (EQNTK) and connect this concept with over-parameterization theory to quantify the convergence of QNNs towards the global optima.
LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection
Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection.
Leveraging GAN Priors for Few-Shot Part Segmentation
Overall, this work is an attempt to explore the internal relevance between generation tasks and perception tasks by prompt designing.
CLNode: Curriculum Learning for Node Classification
Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.
CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing
To tackle this challenge, we propose a framework termed collaborative data-free knowledge distillation via multi-level feature sharing (CDFKD-MFS), which consists of a multi-header student module, an asymmetric adversarial data-free KD module, and an attention-based aggregation module.
Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning
In this paper, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs.
Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition
The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e. g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN).
Hyper-relationship Learning Network for Scene Graph Generation
As a result, HLN significantly improves the performance of scene graph generation by integrating and reasoning from object interactions, relationship interactions, and transitive inference of hyper-relationships.
Schema-Free Dependency Parsing via Sequence Generation
To remedy these drawbacks, we propose to achieve universal and schema-free Dependency Parsing (DP) via Sequence Generation (SG) DPSG by utilizing only the pre-trained language model (PLM) without any auxiliary structures or parsing algorithms.
Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation
To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
ViF-SD2E: A Robust Weakly-Supervised Method for Neural Decoding
Neural decoding plays a vital role in the interaction between the brain and the outside world.
ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
AI engineering has emerged as a crucial discipline to democratize deep neural network (DNN) models among software developers with a diverse background.
Towards understanding the power of quantum kernels in the NISQ era
In this study, we fill this knowledge gap by exploiting the power of quantum kernels when the quantum system noise and sample error are considered.
A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning
To save bandwidth and reduce RTT, VPaaS provides a new video streaming protocol that only sends low-quality video to the cloud.
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment
Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint.
Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud
Combining \underline{v}ideo streaming and online \underline{r}etailing (V2R) has been a growing trend recently.
Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
A multitask loss function is also designed to train both the topic and sentiment prediction models jointly in an end-to-end manner.
Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelligent sensing manner.
Decomposition-Based Transfer Distance Metric Learning for Image Classification
In particular, DTDML learns a sparse combination of the base metrics to construct the target metric by forcing the target metric to be close to an integration of the source metrics.
Multi-view Vector-valued Manifold Regularization for Multi-label Image Classification
In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e. g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e. g. color, texture and shape).
Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples of source and target domain into a common subspace.
Large Margin Multi-modal Multi-task Feature Extraction for Image Classification
The features used in many image analysis-based applications are frequently of very high dimension.
Multi-View Matrix Completion for Multi-Label Image Classification
Therefore, we propose to weightedly combine the MC outputs of different views, and present the multi-view matrix completion (MVMC) framework for transductive multi-label image classification.
Heterogeneous Multi-task Metric Learning across Multiple Domains
Heterogeneous transfer learning approaches can be adopted to remedy this drawback by deriving a metric from the learned transformation across different domains.
Cost-Sensitive Feature Selection by Optimizing F-Measures
Feature selection is beneficial for improving the performance of general machine learning tasks by extracting an informative subset from the high-dimensional features.
Transfer Metric Learning: Algorithms, Applications and Outlooks
Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship.
ResumeNet: A Learning-based Framework for Automatic Resume Quality Assessment
We compare the different variants with our baseline model.
Tensor Canonical Correlation Analysis for Multi-view Dimension Reduction
As a consequence, the high order correlation information contained in the different views is explored and thus a more reliable common subspace shared by all features can be obtained.
