Search Results for author:
Found 49 papers, 25 papers with code
GiFT: Gibbs Fine-Tuning for Code Generation
In this case, the self-generated codes are drawn from a conditional distribution, conditioned on a specific seed description.
HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
Although some recent attempts have been made to handle this task, two major challenges persist: 1) some existing generative methods underperform in high-dimensional multivariate time series forecasting, which is hard to scale to higher dimensions; 2) the inherent high-dimensional multivariate attributes constrain the forecasting lengths of existing generative models.
Learning to Learn Weight Generation via Trajectory Diffusion
Furthermore, we extend the vanilla diffusion algorithm into a trajectory diffusion algorithm to utilize other weights along the optimization trajectory.
InsTex: Indoor Scenes Stylized Texture Synthesis
Generating high-quality textures for 3D scenes is crucial for applications in interior design, gaming, and augmented/virtual reality (AR/VR).
A Generalizable Anomaly Detection Method in Dynamic Graphs
Anomaly detection aims to identify deviations from normal patterns within data.
LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks
Relying on promising watermark recovery accuracies, Deepfake detection is accomplished by assessing the consistency between the content-matched landmark perceptual watermark and the robustly recovered watermark of the suspect image.
Advancing Sustainability via Recommender Systems: A Survey
Human behavioral patterns and consumption paradigms have emerged as pivotal determinants in environmental degradation and climate change, with quotidian decisions pertaining to transportation, energy utilization, and resource consumption collectively precipitating substantial ecological impacts.
Aria: An Open Multimodal Native Mixture-of-Experts Model
Information comes in diverse modalities.
Ranked #5 on
Video Question Answering
on TVBench
Collaboration! Towards Robust Neural Methods for Routing Problems
Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances.
Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification
Based on the above conclusion, we argue a promising future for meta-learning in the unsupervised area, and thus propose DHM-UHT, a dynamic head meta-learning algorithm with unsupervised heterogeneous task construction.
Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation
During client-side local training, FedKD facilitates the low-dimensional student model to mimic the score distribution of triples from the high-dimensional teacher model using KL divergence loss.
A Survey on Natural Language Counterfactual Generation
Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class.
Multi-modal Food Recommendation using Clustering and Self-supervised Learning
Our preliminary investigation of two datasets indicates that pre-trained multi-modal dense representations might precipitate a deterioration in performance compared to ID features when encapsulating interactive relationships.
Communication-Efficient Federated Knowledge Graph Embedding with Entity-Wise Top-K Sparsification
Federated Knowledge Graphs Embedding learning (FKGE) encounters challenges in communication efficiency stemming from the considerable size of parameters and extensive communication rounds.
Personalized Federated Knowledge Graph Embedding with Client-Wise Relation Graph
To address this, we propose Personalized Federated knowledge graph Embedding with client-wise relation Graph (PFedEG), a novel approach that employs a client-wise relation graph to learn personalized embeddings by discerning the semantic relevance of embeddings from other clients.
Beyond Similarity: Personalized Federated Recommendation with Composite Aggregation
Current methods mainly leverage aggregation functions invented by federated vision community to aggregate parameters from similar clients, e. g., clustering aggregation.
Enabling Patient-side Disease Prediction via the Integration of Patient Narratives
Disease prediction holds considerable significance in modern healthcare, because of its crucial role in facilitating early intervention and implementing effective prevention measures.
Multi-modal Learnable Queries for Image Aesthetics Assessment
Instead of directly extracting aesthetic features solely from the image, user comments associated with an image could potentially provide complementary knowledge that is useful for IAA.
Gradient based Feature Attribution in Explainable AI: A Technical Review
Due to the lack of a rigorous definition of explainable AI (XAI), a plethora of research related to explainability, interpretability, and transparency has been developed to explain and analyze the model from various perspectives.
Are ID Embeddings Necessary? Whitening Pre-trained Text Embeddings for Effective Sequential Recommendation
Recent sequential recommendation models have combined pre-trained text embeddings of items with item ID embeddings to achieve superior recommendation performance.
Towards Goal-oriented Prompt Engineering for Large Language Models: A Survey
Large Language Models (LLMs) have shown prominent performance in various downstream tasks and prompt engineering plays a pivotal role in optimizing LLMs' performance.
Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects
The core strength of our pipeline lies in its ability to generate 3D scenes that are not only visually impressive but also exhibit features like photorealism, multi-view consistency, and diversity.
Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search
In code search, the Generation-Augmented Retrieval (GAR) framework, which generates exemplar code snippets to augment queries, has emerged as a promising strategy to address the principal challenge of modality misalignment between code snippets and natural language queries, particularly with the demonstrated code generation capabilities of Large Language Models (LLMs).
BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction
This leads to substantial limitations in existing works of visual stimuli reconstruction from EEG, such as difficulties in aligning EEG embeddings with the fine-grained semantic information and a heavy reliance on additional large self-collected dataset for training.
Efficient Cross-Task Prompt Tuning for Few-Shot Conversational Emotion Recognition
Emotion Recognition in Conversation (ERC) has been widely studied due to its importance in developing emotion-aware empathetic machines.
Computational Efficiency
Emotion Recognition in Conversation
UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models
Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system.
Image Aesthetics Assessment via Learnable Queries
Image aesthetics assessment (IAA) aims to estimate the aesthetics of images.
Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
To our knowledge, this is the first work to explicitly model item popularity in recommendation systems.
Unsupervised Representation Learning for Time Series: A Review
However, there is a lack of systematic analysis of unsupervised representation learning approaches for time series.
Unifying gradient regularization for Heterogeneous Graph Neural Networks
Grug provides a unified framework integrating graph topology and node features, based on which we conduct a detailed theoretical analysis of their effectiveness.
StarNet: Style-Aware 3D Point Cloud Generation
This paper investigates an open research task of reconstructing and generating 3D point clouds.
Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning
We propose a novel Multimodal Pre-training for Sequential Recommendation (MP4SR) framework, which utilizes contrastive losses to capture the correlation among different modality sequences of users, as well as the correlation among different modality sequences of users and items.
Dual Graph Multitask Framework for Imbalanced Delivery Time Estimation
To address the issue, we propose a novel Dual Graph Multitask framework for imbalanced Delivery Time Estimation (DGM-DTE).
A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions
Recommendation systems have become popular and effective tools to help users discover their interesting items by modeling the user preference and item property based on implicit interactions (e. g., purchasing and clicking).
Enhancing Dyadic Relations with Homogeneous Graphs for Multimodal Recommendation
On top of the finding, we propose a model that enhances the dyadic relations by learning Dual RepresentAtions of both users and items via constructing homogeneous Graphs for multimOdal recommeNdation.
Towards AI-Empowered Crowdsourcing
Crowdsourcing, in which human intelligence and productivity is dynamically mobilized to tackle tasks too complex for automation alone to handle, has grown to be an important research topic and inspired new businesses (e. g., Uber, Airbnb).
MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series
Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting.
A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation
Based on this finding, we propose a simple yet effective model, dubbed as FREEDOM, that FREEzes the item-item graph and DenOises the user-item interaction graph simultaneously for Multimodal recommendation.
Ranked #2 on
Multi-modal Recommendation
on Amazon Clothing
Inductive Graph Transformer for Delivery Time Estimation
Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences.
ManiCLIP: Multi-Attribute Face Manipulation from Text
In this paper we present a novel multi-attribute face manipulation method based on textual descriptions.
Reversing Skin Cancer Adversarial Examples by Multiscale Diffusive and Denoising Aggregation Mechanism
Crucially, to further reverse adversarial noises and suppress redundant injected noises, a novel multiscale denoising mechanism is carefully designed that aggregates image information from neighboring scales.
Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective
However, there still lack efforts to evaluate the robustness of such CF systems in deployment.
Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.
Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.
FOCUS: Dealing with Label Quality Disparity in Federated Learning
It maintains a small set of benchmark samples on the FL server and quantifies the credibility of the client local data without directly observing them by computing the mutual cross-entropy between performance of the FL model on the local datasets and that of the client local FL model on the benchmark dataset.
Generating Persuasive Visual Storylines for Promotional Videos
Video contents have become a critical tool for promoting products in E-commerce.
Building Ethics into Artificial Intelligence
As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination.
Balanced Distribution Adaptation for Transfer Learning
To tackle the distribution adaptation problem, in this paper, we propose a novel transfer learning approach, named as Balanced Distribution \underline{A}daptation~(BDA), which can adaptively leverage the importance of the marginal and conditional distribution discrepancies, and several existing methods can be treated as special cases of BDA.
Emotional Attention: A Study of Image Sentiment and Visual Attention
In this paper, we present the first study to focus on the relation between emotional properties of an image and visual attention.
