Search Results for author:
Found 63 papers, 25 papers with code
Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding
To this end, we propose a vision-agnostic safe generation framework, Embedding Sanitizer (ES), which focuses on erasing inappropriate concepts from prompt embeddings and uses the sanitized embeddings to guide the model for safe generation.
Autoregressive Models in Vision: A Survey
Autoregressive modeling has been a huge success in the field of natural language processing (NLP).
Artificial Intelligence of Things: A Survey
We hope this survey will serve as a valuable resource for those engaged in AIoT research and act as a catalyst for future explorations to bridge gaps and drive advancements in this exciting field.
Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion
This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models.
D2O: Dynamic Discriminative Operations for Efficient Generative Inference of Large Language Models
Efficient inference in Large Language Models (LLMs) is impeded by the growing memory demands of key-value (KV) caching, especially for longer sequences.
Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content.
Benchmarking and Boosting Radiology Report Generation for 3D High-Resolution Medical Images
Automatic radiology report generation can significantly benefit the labor-intensive process of report writing by radiologists, especially for 3D radiographs like CT scans, which are crucial for broad clinical diagnostics yet underexplored compared to 2D radiographs.
Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training targets, their last-layer features, together with the classifier weights, will collapse into a stable and symmetric structure.
LuoJiaHOG: A Hierarchy Oriented Geo-aware Image Caption Dataset for Remote Sensing Image-Text Retrival
Image-text retrieval (ITR) plays a significant role in making informed decisions for various remote sensing (RS) applications.
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
The advancements in Large Language Models (LLMs) have been hindered by their substantial sizes, which necessitate LLM compression methods for practical deployment.
MEIT: Multi-Modal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions and is crucial in assisting clinicians.
Search Intenion Network for Personalized Query Auto-Completion in E-Commerce
Query Auto-Completion(QAC), as an important part of the modern search engine, plays a key role in complementing user queries and helping them refine their search intentions. Today's QAC systems in real-world scenarios face two major challenges:1)intention equivocality(IE): during the user's typing process, the prefix often contains a combination of characters and subwords, which makes the current intention ambiguous and difficult to model. 2)intention transfer (IT):previous works make personalized recommendations based on users' historical sequences, but ignore the search intention transfer. However, the current intention extracted from prefix may be contrary to the historical preferences.
The Internet of Things in the Era of Generative AI: Vision and Challenges
Advancements in Generative AI hold immense promise to push Internet of Things (IoT) to the next level.
CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification
In this study we for the first time introduce causal modeling to enhance the robustness of point cloud classification models.
No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models
To reduce the computation cost and the energy consumption in large language models (LLM), skimming-based acceleration dynamically drops unimportant tokens of the input sequence progressively along layers of the LLM while preserving the tokens of semantic importance.
BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
Deep neural networks (DNNs) are susceptible to backdoor attacks, where malicious functionality is embedded to allow attackers to trigger incorrect classifications.
Efficient Large Language Models: A Survey
We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of efficient LLMs research and inspire them to contribute to this important and exciting field.
JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models
In this paper, we present JADE, a targeted linguistic fuzzing platform which strengthens the linguistic complexity of seed questions to simultaneously and consistently break a wide range of widely-used LLMs categorized in three groups: eight open-sourced Chinese, six commercial Chinese and four commercial English LLMs.
FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things
However, most existing FL works do not use datasets collected from authentic IoT devices and thus do not capture unique modalities and inherent challenges of IoT data.
Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
\textsc{Dehydra}), which effectively erases all ten mainstream black-box watermarks from DNNs, with only limited or even no data dependence.
ETP: Learning Transferable ECG Representations via ECG-Text Pre-training
In the domain of cardiovascular healthcare, the Electrocardiogram (ECG) serves as a critical, non-invasive diagnostic tool.
FedMultimodal: A Benchmark For Multimodal Federated Learning
In order to facilitate the research in multimodal FL, we introduce FedMultimodal, the first FL benchmark for multimodal learning covering five representative multimodal applications from ten commonly used datasets with a total of eight unique modalities.
GPT-FL: Generative Pre-trained Model-Assisted Federated Learning
Through comprehensive ablation analysis across various data modalities, we discover that the downstream model generated by synthetic data plays a crucial role in controlling the direction of gradient diversity during FL training, which enhances convergence speed and contributes to the notable accuracy boost observed with GPT-FL.
Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
Med-UniC reaches superior performance across 5 medical image tasks and 10 datasets encompassing over 30 diseases, offering a versatile framework for unifying multi-modal medical data within diverse linguistic communities.
NELoRa-Bench: A Benchmark for Neural-enhanced LoRa Demodulation
The dataset shows that NELoRa can achieve 1. 84-2. 35 dB SNR gain over the standard LoRa decoder.
AutoTaskFormer: Searching Vision Transformers for Multi-task Learning
Vision Transformers have shown great performance in single tasks such as classification and segmentation.
TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training
However, we show empirically that this method can lead to a substantial drop in training accuracy as well as a slower convergence rate.
Exorcising ''Wraith'': Protecting LiDAR-based Object Detector in Automated Driving System from Appearing Attacks
In this paper, we propose a novel plug-and-play defensive module which works by side of a trained LiDAR-based object detector to eliminate forged obstacles where a major proportion of local parts have low objectness, i. e., to what degree it belongs to a real object.
Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation
Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations.
TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images
In this work, we propose an innovative class-agnostic model, namely TopDiG, to directly extract topological directional graphs from remote sensing images and solve these issues.
CAP: Robust Point Cloud Classification via Semantic and Structural Modeling
Recently, deep neural networks have shown great success on 3D point cloud classification tasks, which simultaneously raises the concern of adversarial attacks that cause severe damage to real-world applications.
VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
We explore an efficient approach to establish a foundational video-text model.
Ranked #1 on
Video Captioning
on ActivityNet Captions
(using extra training data)
Adaptive Risk-Aware Bidding with Budget Constraint in Display Advertising
In this work, we explicitly factor in the uncertainty of estimated ad impression values and model the risk preference of a DSP under a specific state and market environment via a sequential decision process.
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical.
Federated Learning Hyper-Parameter Tuning from a System Perspective
In this paper, we propose FedTune, an automatic FL hyper-parameter tuning algorithm tailored to applications' diverse system requirements in FL training.
Client Selection in Federated Learning: Principles, Challenges, and Opportunities
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) has received tremendous attention from both industry and academia.
A Certifiable Security Patch for Object Tracking in Self-Driving Systems via Historical Deviation Modeling
To address this design flaw, we propose a simple yet effective security patch for KF-based MOT, the core of which is an adaptive strategy to balance the focus of KF on observations and predictions according to the anomaly index of the observation-prediction deviation, and has certified effectiveness against a generalized hijacking attack model.
Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model
In this paper, we present a novel insider attack called Matryoshka, which employs an irrelevant scheduled-to-publish DNN model as a carrier model for covert transmission of multiple secret models which memorize the functionality of private ML data stored in local data centers.
Cracking White-box DNN Watermarks via Invariant Neuron Transforms
On $9$ state-of-the-art white-box watermarking schemes and a broad set of industry-level DNN architectures, our attack for the first time reduces the embedded identity message in the protected models to be almost random.
Deep AutoAugment
In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA).
Ranked #2 on
Data Augmentation
on ImageNet
Automatically Generating Counterfactuals for Relation Classification
In this paper, we formulate the problem of automatically generating CAD for RC tasks from an entity-centric viewpoint, and develop a novel approach to derive contextual counterfactuals for entities.
Multiview Transformers for Video Recognition
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations.
Ranked #5 on
Action Classification
on MiT
(using extra training data)
Federated Learning for Internet of Things: Applications, Challenges, and Opportunities
In this paper, we will discuss the opportunities and challenges of FL in IoT platforms, as well as how it can enable diverse IoT applications.
FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated learning (FL) hyper-parameters significantly affect the training overheads in terms of computation time, transmission time, computation load, and transmission load.
Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated Learning (FL) is a distributed model training paradigm that preserves clients' data privacy.
Multi-Scale Feature and Metric Learning for Relation Extraction
Specifically, we first develop a multi-scale convolutional neural network to aggregate the non-successive mainstays in the lexical sequence.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
CATE: Computation-aware Neural Architecture Encoding with Transformers
Our experiments show that CATE is beneficial to the downstream search, especially in the large search space.
Exploring the Security Boundary of Data Reconstruction via Neuron Exclusivity Analysis
Among existing privacy attacks on the gradient of neural networks, \emph{data reconstruction attack}, which reverse engineers the training batch from the gradient, poses a severe threat on the private training data.
Deep Learning in the Era of Edge Computing: Challenges and Opportunities
The era of edge computing has arrived.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize architecture search on such representations which incurs search bias.
Ranked #10 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-100
Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
In this paper, we formalize the music-conditioned dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance.
Ranked #1 on
Motion Synthesis
on BRACE
Transfer learning in large-scale ocean bottom seismic wavefield reconstruction
Because different frequency slices share information, we propose the use the method of transfer training to make our approach computationally more efficient by warm starting the training with CNN weights obtained from a neighboring frequency slices.
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime.
A closer look at network resolution for efficient network design
We propose a framework to mutually learn from different input resolutions and network widths.
HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.
How Sequence-to-Sequence Models Perceive Language Styles?
Style is ubiquitous in our daily language uses, while what is language style to learning machines?
NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
These systems usually run multiple applications concurrently and their available resources at runtime are dynamic due to events such as starting new applications, closing existing applications, and application priority changes.
Theoretical Analysis of Image-to-Image Translation with Adversarial Learning
Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners.
DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation
There is an undeniable communication barrier between deaf people and people with normal hearing ability.
Line-Based Multi-Label Energy Optimization for Fisheye Image Rectification and Calibration
Fisheye image rectification and estimation of intrinsic parameters for real scenes have been addressed in the literature by using line information on the distorted images.
