Search Results for author:
Found 103 papers, 28 papers with code
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
In this paper, we analyze attention patterns in reasoning tasks and reveal a Token Importance Recurrence phenomenon: a large proportion of tokens receive renewed attention after multiple decoding steps, which is failed to capture by existing works and may lead to unpredictable eviction on such periodically critical tokens.
Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-level rewards that struggle to capture local structure details.
FreeMesh: Boosting Mesh Generation with Coordinates Merging
We hope that the proposed PTME and coordinate merging can enhance the existing mesh tokenizers and guide the further development of native mesh generation.
D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving
The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead.
BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations.
Towards Robust and Realistic Human Pose Estimation via WiFi Signals
Robust WiFi-based human pose estimation is a challenging task that bridges discrete and subtle WiFi signals to human skeletons.
RORem: Training a Robust Object Remover with Human-in-the-Loop
We first collect 60K training pairs from open-source datasets to train an initial object removal model for generating removal samples, and then utilize human feedback to select a set of high-quality object removal pairs, with which we train a discriminator to automate the following training data generation process.
Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey
The integration of facial expression analysis with Internet-of-Thing (IoT) systems has significant potential across diverse scenarios.
Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues.
Advanced Video Inpainting Using Optical Flow-Guided Efficient Diffusion
Specifically, FloED employs a dual-branch architecture, where a flow branch first restores corrupted flow and a multi-scale flow adapter provides motion guidance to the main inpainting branch.
Random Sampling for Diffusion-based Adversarial Purification
Remarkably, under strong attack, our DiffAP even achieves a more than 20% robustness advantage with 10$\times$ sampling acceleration.
Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
To address these issues, we propose a novel dyNamically Evolving dUal skeleton-semantic syneRgistic framework with the guidance of cOntext-aware side informatioN (dubbed Neuron), to explore more fine-grained cross-modal correspondence from micro to macro perspectives at both spatial and temporal levels, respectively.
Spider: Any-to-Many Multimodal LLM
To address this limitation, we introduce Spider, a novel efficient Any-to-Many Modalities Generation (AMMG) framework, which can generate an arbitrary combination of modalities 'Text + Xs', such as Text + {Image and Audio and Video}.
A QoE-Aware Split Inference Accelerating Algorithm for NOMA-based Edge Intelligence
Thus, the model split inference is proposed to improve the performance of edge intelligence, in which the AI model is divided into different sub models and the resource-intensive sub model is offloaded to edge server wirelessly for reducing resource requirements and inference latency.
Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning
This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein the model is trained to recognize multiple unseen classes within a sample (e. g., an image) based on seen classes and auxiliary knowledge, e. g., semantic information.
Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches
Additionally, large-scale foundation models have expanded to create images, audio, videos, and multi-modal contents, further emphasizing the need for efficient deployment.
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel state-object compositions by leveraging the shared knowledge of their primitive components.
RTAT: A Robust Two-stage Association Tracker for Multi-Object Tracking
Data association is an essential part in the tracking-by-detection based Multi-Object Tracking (MOT).
On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey
Zero-shot image recognition (ZSIR) aims to recognize and reason in unseen domains by learning generalized knowledge from limited data in the seen domain.
Detached and Interactive Multimodal Learning
Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data.
Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion
By constructing a surrogate client model that captures the structure of perturbed gradients, we obtain crucial gradient data for training the diffusion model.
How far are today's time-series models from real-world weather forecasting applications?
As a result, it enables a better training of models and a more accurate assessment of the real-world forecasting capabilities of TSF models, pushing them closer to in-situ applications.
IRASim: Learning Interactive Real-Robot Action Simulators
We hope that IRASim can serve as an effective and scalable approach to enhance robot learning in the real world.
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection
To tackle this issue, we dive into the fundamental mechanism of backdoor attacks on FSSL, proposing the Embedding Inspector (EmInspector) that detects malicious clients by inspecting the embedding space of local models.
CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer
To mitigate this issue, we introduce an efficient neural codec, the Variational Autoencoder Transformer (VAEformer), for extreme compression of climate data to significantly reduce data storage cost, making AI-based meteorological research portable to researchers.
Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models
Text-driven diffusion models have significantly advanced the image editing performance by using text prompts as inputs.
DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target domain) is absent from the decentralized training data (source domains).
EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
For instance, on the Wikitext2 dataset with LlamaV1-7B at 70% sparsity, our proposed EBFT achieves a perplexity of 16. 88, surpassing the state-of-the-art DSnoT with a perplexity of 75. 14.
Expediting In-Network Federated Learning by Voting-Based Consensus Model Compression
Recently, federated learning (FL) has gained momentum because of its capability in preserving data privacy.
FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting
Therefore, building a kilometer-scale global forecast model is a persistent pursuit in the meteorology domain.
C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation
We empirically reveal that the modality gap i. e. modality imbalance and soft label misalignment incurs the ineffectiveness of traditional KD in CMKD.
Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection
On the other hand, we propose the modality selection aiming to select subsets of local modalities with great diversity and achieving global modal balance simultaneously.
Balanced Multi-modal Federated Learning via Cross-Modal Infiltration
Federated learning (FL) underpins advancements in privacy-preserving distributed computing by collaboratively training neural networks without exposing clients' raw data.
Mobility and Cost Aware Inference Accelerating Algorithm for Edge Intelligence
The model segmentation without user mobility has been investigated deeply by previous works.
High Efficiency Inference Accelerating Algorithm for NOMA-based Mobile Edge Computing
Specifically, when the mobile user has a large model inference task needed to be calculated in the NOMA-based MEC, it will take the energy consumption of both device and edge server and the inference latency into account to find the optimal model split strategy, subchannel allocation strategy (uplink and downlink), and transmission power allocation strategy (uplink and downlink).
QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation
We introduce QuickDrop, an efficient and original FU method that utilizes dataset distillation (DD) to accelerate unlearning and drastically reduces computational overhead compared to existing approaches.
FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model
Specifically, we find that the very last few steps of the denoising (i. e., generation) process strongly correspond to the stylistic information of images, and based on this, we propose to augment the latent features of both the foreground and background images with Gaussians for a direct denoising-based harmonization.
Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning
In this paper, we propose a simple yet effective Attribute-Aware Representation Rectification framework for GZSL, dubbed $\mathbf{(AR)^{2}}$, to adaptively rectify the feature extractor to learn novel features while keeping original valuable features.
A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability
Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push the capabilities of AI to the network edge for real-time, efficient and secure intelligent decision-making and computation.
Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding
However, the domain discrepancy and data scarcity problems among clients deteriorate the performance of the global FL model.
Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models
To this end, Compresso prunes LLaMA-7B to 5. 4B, maintaining original performance and even surpassing LLaMA-7B in reading comprehension by 2. 62%.
GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning
That is, in the process of inferring unseen classes, global features represent the principal direction of the image in the feature space, while local features should maintain uniqueness within a certain range.
Intelligence-Endogenous Management Platform for Computing and Network Convergence
Therefore, in this article, we present the concept of an intelligence-endogenous management platform for CNCs called \emph{CNC brain} based on artificial intelligence technologies.
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
Theoretically, we show the convergence guarantee of the dual regulators.
SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection
In this paper, we introduce Semantic Reasoning with Compound Domains (SRCD) for Single-DGOD.
Ranked #6 on
Robust Object Detection
on DWD
Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices.
On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directions
As Federated Learning (FL) has gained increasing attention, it has become widely acknowledged that straightforwardly applying stochastic gradient descent (SGD) on the overall framework when learning over a sequence of tasks results in the phenomenon known as ``catastrophic forgetting''.
Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resolution (SR) tasks.
SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization
Based on the idea that in-distribution (ID) data with spurious features may have a lower experience risk, in this paper, we propose a novel Spurious Feature-targeted model Pruning framework, dubbed SFP, to automatically explore invariant substructures without referring to the above drawbacks.
DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning
Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples.
CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario
Previous works usually assume the malware families are known to the classifier in a close-set scenario, i. e., testing families are the subset or at most identical to training families.
Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
However, it suffers from issues in terms of communication, resource of MTs, and privacy.
MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition
Malware open-set recognition (MOSR) aims at jointly classifying malware samples from known families and detect the ones from novel unknown families, respectively.
Towards Unbiased Training in Federated Open-world Semi-supervised Learning
Federated Semi-supervised Learning (FedSSL) has emerged as a new paradigm for allowing distributed clients to collaboratively train a machine learning model over scarce labeled data and abundant unlabeled data.
Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement
In this paper, we propose a novel Dual-prototype Self-augment and Refinement method (DSR) for NO-CL problem, which consists of two strategies: 1) Dual class prototypes: vanilla and high-dimensional prototypes are exploited to utilize the pre-trained information and obtain robust quasi-orthogonal representations rather than example buffers for both privacy preservation and memory reduction.
DualMix: Unleashing the Potential of Data Augmentation for Online Class-Incremental Learning
Unfortunately, OCI learning can suffer from catastrophic forgetting (CF) as the decision boundaries for old classes can become inaccurate when perturbated by new ones.
Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning
Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance.
Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models
Federated learning (FL) is an emerging technique that trains massive and geographically distributed edge data while maintaining privacy.
(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning
Recent studies usually approach multi-label zero-shot learning (MLZSL) with visual-semantic mapping on spatial-class correlation, which can be computationally costly, and worse still, fails to capture fine-grained class-specific semantics.
Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle
In this paper, we try to solve this problem by introducing a principled and unified framework based on Information Bottleneck (IB) theory, which further guides us to an automatic pruning approach.
Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning
Recent studies show that even highly biased dense networks contain an unbiased substructure that can achieve better out-of-distribution (OOD) generalization than the original model.
Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning
Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.
Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning
Recently, data heterogeneity among the training datasets on the local clients (a. k. a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle it.
Out-of-Distribution Generalization
Personalized Federated Learning
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning
Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which induces a tremendously large output space containing all possible state-object compositions.
Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
Existing methods either learn the combined state-object representation, challenging the generalization of unseen compositions, or design two classifiers to identify state and object separately from image features, ignoring the intrinsic relationship between them.
FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers
Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.
CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming
Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth.
PMR: Prototypical Modal Rebalance for Multimodal Learning
Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations.
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning
We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application
In contrast, visual data exhibits a fundamentally different structure: Its basic unit (pixel) is a natural low-level representation with significant redundancies in the neighbourhood, which poses obvious challenges to the interpretability of MSA mechanism in ViT.
PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model
Quick global aggregation of effective distributed parameters is crucial to federated learning (FL), which requires adequate bandwidth for parameters communication and sufficient user data for local training.
Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network
Concretely, we maintain an edge-agnostic hidden model in the cloud server to estimate a less-accurate while direction-aware inversion of the global model.
A Survey on Collaborative DNN Inference for Edge Intelligence
With the vigorous development of artificial intelligence (AI), the intelligent applications based on deep neural network (DNN) change people's lifestyles and the production efficiency.
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions
In particular, we dig out some critical ingredients from the iteration-based attacks, including data initialization, model training and gradient matching.
Anchor Sampling for Federated Learning with Partial Client Participation
The lack of inactive clients' updates in partial client participation makes it more likely for the model aggregation to deviate from the aggregation based on full client participation.
Rethinking Classifier and Adversarial Attack
Various defense models have been proposed to resist adversarial attack algorithms, but existing adversarial robustness evaluation methods always overestimate the adversarial robustness of these models (i. e., not approaching the lower bound of robustness).
CE-based white-box adversarial attacks will not work using super-fitting
This is especially dangerous for some systems with high-security requirements, so this paper proposes a new defense method by using the model super-fitting state to improve the model's adversarial robustness (i. e., the accuracy under adversarial attacks).
Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds.
Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention
We argue that disregarding the connection between major and minor classes, i. e., correspond to the global and local information, respectively, is the cause of the problem.
Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations
Existing studies of machine unlearning mainly focus on sample-wise unlearning, such that a learnt model will not expose user's privacy at the sample level.
A Coalition Formation Game Approach for Personalized Federated Learning
Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot.
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources.
Parameterized Knowledge Transfer for Personalized Federated Learning
To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients.
Federated Unlearning via Class-Discriminative Pruning
Evaluated on CIFAR10 dataset, our method accelerates the speed of unlearning by 8. 9x for the ResNet model, and 7. 9x for the VGG model under no degradation in accuracy, compared to retraining from scratch.
SDN-based Resource Allocation in Edge and Cloud Computing Systems: An Evolutionary Stackelberg Differential Game Approach
Based on this dynamic access model, a Stackelberg differential game based cloud computing resource sharing mechanism is proposed to facilitate the resource trading between the cloud computing service provider (CCP) and different edge computing service providers (ECPs).
Personalized Federated Learning with Contextualized Generalization
The prevalent personalized federated learning (PFL) usually pursues a trade-off between personalization and generalization by maintaining a shared global model to guide the training process of local models.
Decentralized Federated Learning for UAV Networks: Architecture, Challenges, and Opportunities
Unmanned aerial vehicles (UAVs), or say drones, are envisioned to support extensive applications in next-generation wireless networks in both civil and military fields.
Online Multiple Object Tracking with Cross-Task Synergy
On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts.
DPN: Detail-Preserving Network with High Resolution Representation for Efficient Segmentation of Retinal Vessels
2) The segmentation speed of DPN is over 20-160 times faster than other methods on the DRIVE dataset.
Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework
This framework can achieve scalable and flexible decentralized FEL by individually manage local model updates or model sharing records for performance isolation.
Cryptography and Security
A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
One common practice in zero-shot learning is to train a projection between the visual and semantic feature spaces with labeled seen classes examples.
Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
In the dynamic environment, the mobile devices selected by the existing reactive candidate-selection algorithms very possibly fail to complete the training and reporting phases of FL, because the FL parameter server only knows the currently-observed resources of all candidates.
Intermittent Pulling with Local Compensation for Communication-Efficient Federated Learning
A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale Federated Learning is the communication overhead on pushing local gradients and pulling global model.
PIRATE: A Blockchain-based Secure Framework of Distributed Machine Learning in 5G Networks
Therefore, to provide the byzantine-resilience for distributed learning in 5G era, this article proposes a secure computing framework based on the sharding-technique of blockchain, namely PIRATE.
Distributed, Parallel, and Cluster Computing Cryptography and Security
Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions
The new demands for high-reliability and ultra-high capacity wireless communication have led to extensive research into 5G communications.
MAANet: Multi-view Aware Attention Networks for Image Super-Resolution
Specifically, we propose the local aware (LA) and global aware (GA) attention to deal with LR features in unequal manners, which can highlight the high-frequency components and discriminate each feature from LR images in the local and the global views, respectively.
Position-Aware Convolutional Networks for Traffic Prediction
Our approach employs the inception backbone network to capture rich features of traffic distribution on the whole area.
AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learning
It considers the Alignment of Manifold Structures by Semantic Feature Expansion.
EE-AE: An Exclusivity Enhanced Unsupervised Feature Learning Approach
In order to deal with this issue, we propose an Exclusivity Enhanced (EE) unsupervised feature learning approach to improve the conventional AE.
Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition
To the best of our knowledge, our work is the first to consider the adaptive adjustment of semantic FS in ZSR.
Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training
Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models.
BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation
Results: The proposed BTS-DSN has been verified on DRIVE, STARE and CHASE_DB1 datasets, and showed competitive performance over other state-of-the-art methods.
