Search Results for author:
Found 39 papers, 9 papers with code
IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting
Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Class-Incremental Learning (MCIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived.
Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning
We evaluated the system in real-world medical scenarios.
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
Large language models (LLMs) based agent systems have made great strides in real-world applications beyond traditional NLP tasks.
Modeling the residual queue and queue-dependent capacity in a static traffic assignment problem
To address this critical issue, we introduce a novel static traffic assignment model that explicitly incorporates the residual queue and queue-dependent link capacity.
FedCross: Intertemporal Federated Learning Under Evolutionary Games
Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally.
TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning
However, in the context of semi-decentralized FL, clients' communication and training states are dynamic.
Out-of-Distribution Detection with Overlap Index
Lastly, we show that the proposed OI-based confidence score function inherits nice properties from OI (e. g., insensitivity to small distributional variations and robustness against Huber $\epsilon$-contamination) and is a versatile tool for estimating OI and model accuracy in specific contexts.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Adaptive Domain Learning for Cross-domain Image Denoising
To address this cross-domain challenge, we present a novel adaptive domain learning (ADL) scheme for cross-domain RAW image denoising by utilizing existing data from different sensors (source domain) plus a small amount of data from the new sensor (target domain).
StringLLM: Understanding the String Processing Capability of Large Language Models
In particular, we first propose StringLLM, a method to construct datasets for benchmarking string processing capability of LLMs.
Combining Switching Mechanism with Re-Initialization and Anomaly Detection for Resiliency of Cyber-Physical Systems
An anomaly detector is used to detect CPS attacks during the controller's working period.
TextToucher: Fine-Grained Text-to-Touch Generation
We model these granularities of information through text descriptions and propose a fine-grained Text-to-Touch generation method (TextToucher) to generate high-quality tactile samples.
Rethinking Attention Module Design for Point Cloud Analysis
In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis.
Can Dense Connectivity Benefit Outlier Detection? An Odyssey with NAS
In this work, we propose a novel paradigm, Dense Connectivity Search of Outlier Detector (DCSOD), that automatically explore the dense connectivity of CNN architectures on near-OOD detection task using Neural Architecture Search (NAS).
CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring
Detection of out-of-distribution (OOD) samples is crucial for safe real-world deployment of machine learning models.
Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels
The ambiguous appearance, tiny scale, and fine-grained classes of objects in remote sensing imagery inevitably lead to the noisy annotations in category labels of detection dataset.
Seeing Text in the Dark: Algorithm and Benchmark
Localizing text in low-light environments is challenging due to visual degradations.
Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection
Having the computed five metrics, five novelty detectors are trained from the validation dataset.
Integrity and Junkiness Failure Handling for Embedding-based Retrieval: A Case Study in Social Network Search
Embedding based retrieval has seen its usage in a variety of search applications like e-commerce, social networking search etc.
A Deep Neural Network Algorithm for Linear-Quadratic Portfolio Optimization with MGARCH and Small Transaction Costs
When $\epsilon$ is small, we can implement an NN algorithm based on the expansion of the solution in powers of $\epsilon$.
An Upper Bound for the Distribution Overlap Index and Its Applications
In domain shift analysis, we propose a theorem based on our bound.
Privacy-Preserving Collaborative Learning through Feature Extraction
As a baseline, in Cooperatively Trained Feature Extractor (CTFE) Learning, the entities train models by sharing raw data.
Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation
In particular: 1) existing methods do not explicitly encode and capture the evolution of short-term preference as sequential methods do; 2) simply using last few interactions is not enough for modeling the changing trend.
Robust Adaptive Beamforming via Worst-Case SINR Maximization with Nonconvex Uncertainty Sets
Then a linear matrix inequality (LMI) relaxation for the QMI problem is proposed, with an additional valid linear constraint.
HMRNet: High and Multi-Resolution Network with Bidirectional Feature Calibration for Brain Structure Segmentation in Radiotherapy
Accurate segmentation of Anatomical brain Barriers to Cancer spread (ABCs) plays an important role for automatic delineation of Clinical Target Volume (CTV) of brain tumors in radiotherapy.
Fetal Brain Tissue Annotation and Segmentation Challenge Results
Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context.
Stylistic Retrieval-based Dialogue System with Unparallel Training Data
The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction.
Denoising User-aware Memory Network for Recommendation
Specifically, the framework: (i) proposes a feature purification module based on orthogonal mapping, which use the representation of explicit feedback to purify the representation of implicit feedback, and effectively denoise the implicit feedback; (ii) designs a user memory network to model the long-term interests in a fine-grained way by improving the memory network, which is ignored by the existing methods; and (iii) develops a preference-aware interactive representation component to fuse the long-term and short-term interests of users based on gating to understand the evolution of unbiased preferences of users.
LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding
In this work, we propose a knowledge distillation method LRC-BERT based on contrastive learning to fit the output of the intermediate layer from the angular distance aspect, which is not considered by the existing distillation methods.
Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images
To address this problem, we present a one-shot framework for organ and landmark localization in volumetric medical images, which does not need any annotation during the training stage and could be employed to locate any landmarks or organs in test images given a support (reference) image during the inference stage.
Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection
This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers.
Improving Text Generation with Student-Forcing Optimal Transport
An extension is further proposed to improve the OT learning, based on the structural and contextual information of the text sequences.
Towards Learning-automation IoT Attack Detection through Reinforcement Learning
These low-rate attacks are challenging to detect and can persist in the networks.
Drosophila-Inspired 3D Moving Object Detection Based on Point Clouds
3D moving object detection is one of the most critical tasks in dynamic scene analysis.
"Love is as Complex as Math": Metaphor Generation System for Social Chatbot
By embedding the framework into a chatbot system, we then enables the chatbot to communicate with users using figurative language.
Non-imaging single-pixel sensing with optimized binary modulation
The conventional high-level sensing techniques require high-fidelity images as input to extract target features, which are produced by either complex imaging hardware or high-complexity reconstruction algorithms.
Lidar-based Object Classification with Explicit Occlusion Modeling
Object detection and classification based on lidar point cloud is a key technology for UGV.
Thinkey: A Scalable Blockchain Architecture
This paper presents Thinkey, an efficient, secure, infinitely scalable and decentralized blockchain architecture.
Cryptography and Security
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks.
Incorporating Topic Aspects for Online Comment Convincingness Evaluation
In this paper, we propose to incorporate topic aspects information for online comments convincingness evaluation.
