Search Results for author:
Found 35 papers, 14 papers with code
Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch.
Graph Foundation Models for Recommendation: A Comprehensive Survey
Recommender systems (RS) serve as a fundamental tool for navigating the vast expanse of online information, with deep learning advancements playing an increasingly important role in improving ranking accuracy.
A Transformer Model for Segmentation, Classification, and Caller Identification of Marmoset Vocalization
Marmoset, a highly vocalized primate, has become a popular animal model for studying social-communicative behavior and its underlying mechanism comparing with human infant linguistic developments.
MuseTalk: Real-Time High Quality Lip Synchronization with Latent Space Inpainting
We propose MuseTalk, which generates lip-sync targets in a latent space encoded by a Variational Autoencoder, enabling high-fidelity talking face video generation with efficient inference.
SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
To address these limitations, we introduce SciSafeEval, a comprehensive benchmark designed to evaluate the safety alignment of LLMs across a range of scientific tasks.
State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Survey
With the continuous breakthroughs in core technology, the dawn of large-scale integration of robotic systems into daily human life is on the horizon.
Preference Distillation for Personalized Generative Recommendation
Recently, researchers have investigated the capabilities of Large Language Models (LLMs) for generative recommender systems.
Entropy-Based Decoding for Retrieval-Augmented Large Language Models
Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses.
Understanding the Role of User Profile in the Personalization of Large Language Models
Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to enhance the performance on a wide range of tasks.
Instruction Tuning With Loss Over Instructions
We observe that IM is especially beneficial when trained on datasets with lengthy instructions paired with brief outputs, or under the Superficial Alignment Hypothesis (SAH) where a small amount of training examples are used for instruction tuning.
AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models
Given the importance of ancient Chinese in capturing the essence of rich historical and cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate benchmarks that can effectively evaluate their understanding of ancient contexts.
SplitGNN: Spectral Graph Neural Network for Fraud Detection against Heterophily
However, researches on addressing the heterophily problem in the spectral domain are still limited due to a lack of understanding of spectral energy distribution in graphs with heterophily.
Ranked #1 on
Fraud Detection
on FDCompCN
Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding
This model adeptly selects frames pertinent to queries, obviating the need for a complete movie-level knowledge graph.
Graph Sampling-based Meta-Learning for Molecular Property Prediction
To effectively utilize many-to-many correlations of molecules and properties, we propose a Graph Sampling-based Meta-learning (GS-Meta) framework for few-shot molecular property prediction.
OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting
Extensive experiments on real-world benchmark datasets for downstream time series anomaly detection and forecasting tasks demonstrate that OneShotSTL is from 10 to over 1, 000 times faster than the state-of-the-art methods, while still providing comparable or even better accuracy.
Cross-modal information fusion for voice spoofing detection
Researchers have proposed many methods to defend against these attacks, but in the existing methods, researchers just focus on speech features.
Ranked #1 on
Voice Anti-spoofing
on ASVspoof 2019 - PA
General non-linear imitation leads to limit cycles in eco-evolutionary dynamics
We extrapolate from the linear imitation function to general imitation function, which can be non-linear.
Dynamic graph neural network for fake news detection
To address these shortcomings, we proposed a dynamic propagation graph-based fake news detection method to capture the missing dynamic propagation information in static networks and classify fake news.
MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysis
Existing deep approaches try to bridge the gap by directly learning discrimination among emotions globally in one shot without considering the hierarchical relationship among emotions at different affective levels and the affective level of emotions to be classified.
Prediction of Depression Severity Based on the Prosodic and Semantic Features with Bidirectional LSTM and Time Distributed CNN
For the text modality, we use global vectors for word representation (GloVe) to perform word embeddings and the embeddings are fed into the Bi-LSTM network.
Relation-aware Hierarchical Attention Framework for Video Question Answering
Video Question Answering (VideoQA) is a challenging video understanding task since it requires a deep understanding of both question and video.
Factorization and transverse phase-space parton distributions
By modelling non-perturbative modes in thickness beam functions of large nuclei in heavy-ion collisions, the factorization formula confirms the cross section in the Glauber model for hard processes.
High Energy Physics - Phenomenology High Energy Physics - Experiment Nuclear Experiment Nuclear Theory
Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition
To tackle the challenges above, we propose a novel Frame Aggregation and Multi-Modal Fusion (FAMF) framework for video-based person recognition, which aggregates face features and incorporates them with multi-modal information to identify persons in videos.
Sparse-data based 3D surface reconstruction with vector matching
Three dimensional surface reconstruction based on two dimensional sparse information in the form of only a small number of level lines of the surface with moderately complex structures, containing both structured and unstructured geometries, is considered in this paper.
Iterative regularization algorithms for image denoising with the TV-Stokes model
We propose a set of iterative regularization algorithms for the TV-Stokes model to restore images from noisy images with Gaussian noise.
Multidimensional TV-Stokes for image processing
A complete multidimential TV-Stokes model is proposed based on smoothing a gradient field in the first step and reconstruction of the multidimensional image from the gradient field.
Alternating minimization for a single step TV-Stokes model for image denoising
A convergence analysis is given.
DeepRec: An Open-source Toolkit for Deep Learning based Recommendation
In this toolkit, we have implemented a number of deep learning based recommendation algorithms using Python and the widely used deep learning package - Tensorflow.
Flow in AA and pA as an interplay of fluid-like and non-fluid like excitations
To study the microscopic structure of quark-gluon plasma, data from hadronic collisions must be confronted with models that go beyond fluid dynamics.
High Energy Physics - Phenomenology High Energy Physics - Experiment Nuclear Experiment Nuclear Theory
Low-cost Measurement of Industrial Shock Signals via Deep Learning Calibration
The results show that the proposed network is capable to map low-end shock signals to its high-end counterparts with satisfactory accuracy.
Hierarchical Macro Strategy Model for MOBA Game AI
In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games.
Gated Attentive-Autoencoder for Content-Aware Recommendation
In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder.
Deep Meta-Learning: Learning to Learn in the Concept Space
Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks.
HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks
Similarity search is an important function in many applications, which usually focuses on measuring the similarity between objects with the same type.
Correlative Multi-Label Multi-Instance Image Annotation
The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.
