Search Results for author:
Found 68 papers, 25 papers with code
PyG-SSL: A Graph Self-Supervised Learning Toolkit
Graph Self-Supervised Learning (SSL) has emerged as a pivotal area of research in recent years.
APEX$^2$: Adaptive and Extreme Summarization for Personalized Knowledge Graphs
Furthermore, when the size constraint of PKG is extremely small, the existing methods cannot distinguish which facts are more of immediate interest and guarantee the utility of the summarized PKG.
Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?
In this work, to address these issues, we leverage multi-modal prompt learning to effectively adapt pre-trained GNN to downstream tasks and data, given only a few semantically labeled samples, each with extremely weak text supervision.
Provably Extending PageRank-based Local Clustering Algorithm to Weighted Directed Graphs with Self-Loops and to Hypergraphs
Specifically, leveraging PageRank, we propose two algorithms: GeneralACL for graphs and HyperACL for hypergraphs.
Why Anticipatory Sensing Matters in Commercial ACC Systems under Cut-In Scenarios: A Perspective from Stochastic Safety Analysis
The theoretical analysis demonstrates that the vehicle state evolution and the corresponding safety of ACC in cut-in situations are influenced by multiple factors, including the original leading vehicle's state, the initial conditions of the cut-in vehicle, subsequent cut-in maneuvers, sensing delays, and the ACC's anticipation capabilities.
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Transformers have achieved great success in recent years.
MaLei at the PLABA Track of TAC-2024: RoBERTa for Task 1 -- LLaMA3.1 and GPT-4o for Task 2
This report contains two sections corresponding to the two sub-tasks in PLABA 2024.
PageRank Bandits for Link Prediction
Link prediction is a critical problem in graph learning with broad applications such as recommender systems and knowledge graph completion.
Global Convergence in Training Large-Scale Transformers
First, we construct the mean-field limit of large-scale Transformers, showing that as the model width and depth go to infinity, gradient flow converges to the Wasserstein gradient flow, which is represented by a partial differential equation.
Hypergraphs as Weighted Directed Self-Looped Graphs: Spectral Properties, Clustering, Cheeger Inequality
Then, we prove that the normalized hypergraph Laplacian is associated with the NCut value, which inspires our HyperClus-G algorithm for spectral clustering on EDVW hypergraphs.
Real-time Vehicle-to-Vehicle Communication Based Network Cooperative Control System through Distributed Database and Multimodal Perception: Demonstrated in Crossroads
The autonomous driving industry is rapidly advancing, with Vehicle-to-Vehicle (V2V) communication systems highlighting as a key component of enhanced road safety and traffic efficiency.
Parametric Graph Representations in the Era of Foundation Models: A Survey and Position
Graphs have been widely used in the past decades of big data and AI to model comprehensive relational data.
EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
In this work, we introduce EMMA-500, a large-scale multilingual language model continue-trained on texts across 546 languages designed for enhanced multilingual performance, focusing on improving language coverage for low-resource languages.
Graph and Sequential Neural Networks in Session-based Recommendation: A Survey
Recent years have witnessed the remarkable success of recommendation systems (RSs) in alleviating the information overload problem.
BeeManc at the PLABA Track of TAC-2023: Investigating LLMs and Controllable Attributes for Improving Biomedical Text Readability
In the official human evaluation, our model BART-w-CTs ranks 2nd on Sentence-Simplicity (score 92. 84), 3rd on Term-Simplicity (score 82. 33) among all 7 evaluated systems; It also produced a high score 91. 57 on Fluency in comparison to the highest score 93. 53.
Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research
Overall, this study pioneered evaluating LLMs in water engineering and research by introducing the WaterER benchmark to assess the trustworthiness of their predictions.
A Comparison of Language Modeling and Translation as Multilingual Pretraining Objectives
We ensure that training data and model architectures are comparable, and discuss the downstream performances across 6 languages that we observe in probing and fine-tuning scenarios.
Mapping the Scholarship of Dark Pattern Regulation: A Systematic Review of Concepts, Regulatory Paradigms, and Solutions from an Interdisciplinary Perspective
This research critically discusses the current barriers to effective dark pattern regulations and explores promising regulatory solutions.
Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation
In this paper, we propose a Global Attention-guided Dual-domain Feature Learning network (GAD) to address the above-mentioned issues.
ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation
Remarkably, it secures up to a 4. 95% increase in accuracy on the CIFAR100 compared to its directly trained counterparts, even surpassing the performance of multiplicative NNs.
Efficient Sparse Attention needs Adaptive Token Release
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks.
Enhancing Counterfactual Image Generation Using Mahalanobis Distance with Distribution Preferences in Feature Space
By employing information fusion techniques, our method maximizes the use of data to address feature counterfactual explanations in the feature space.
SpherE: Expressive and Interpretable Knowledge Graph Embedding for Set Retrieval
We show that the set retrieval highly depends on expressive modeling of many-to-many relations, and propose a new KG embedding model SpherE to address this problem.
Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
Besides, the experiments show that there is a strong correlation between the LLM's performance in different languages and the proportion of those languages in its pre-training corpus.
Multi-level Graph Subspace Contrastive Learning for Hyperspectral Image Clustering
Multi-level graph subspace contrastive learning: multi-level contrastive learning was conducted to obtain local-global joint graph representations, to improve the consistency of the positive samples between views, and to obtain more robust graph embeddings.
S2RC-GCN: A Spatial-Spectral Reliable Contrastive Graph Convolutional Network for Complex Land Cover Classification Using Hyperspectral Images
Specifically, we fused the spectral and spatial features extracted by the 1D- and 2D-encoder, and the 2D-encoder includes an attention model to automatically extract important information.
Heterogeneous Contrastive Learning for Foundation Models and Beyond
In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive self-supervised learning to model large-scale heterogeneous data.
Interpretable Machine Learning for Weather and Climate Prediction: A Survey
Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction.
Diffusion Model for Data-Driven Black-Box Optimization
In this paper, we focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization over complex structured variables.
VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework
With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question.
VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding
It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts.
WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs
Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content.
Regularized DeepIV with Model Selection
In this paper, we study nonparametric estimation of instrumental variable (IV) regressions.
Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties.
Multiview Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks
In conclusion, the proposed model can effectively improve the clustering ac-curacy of HSI.
Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning
Designing algorithms for a constrained convex MDP faces several challenges, including (1) handling the large state space, (2) managing the exploration/exploitation tradeoff, and (3) solving the constrained optimization where the objective and the constraint are both nonlinear functions of the visitation measure.
Overview of Sensing Attacks on Autonomous Vehicle Technologies and Impact on Traffic Flow
While perception systems in Connected and Autonomous Vehicles (CAVs), which encompass both communication technologies and advanced sensors, promise to significantly reduce human driving errors, they also expose CAVs to various cyberattacks.
ChemDFM: A Large Language Foundation Model for Chemistry
In its utmost form, such a generalist AI chemist could be referred to as Chemical General Intelligence.
Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clustering
The pixel-level contrastive learning method can effectively improve the ability of the model to capture fine features of HSI but requires a large time overhead.
Contrastive Multi-view Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks
In this study, contrastive multi-view subspace clustering of HSI was proposed based on graph convolutional networks.
UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework
In the current landscape of artificial intelligence, foundation models serve as the bedrock for advancements in both language and vision domains.
Mapping the Empirical Evidence of the GDPR (In-)Effectiveness: A Systematic Review
In the realm of data protection, a striking disconnect prevails between traditional domains of doctrinal, legal, theoretical, and policy-based inquiries and a burgeoning body of empirical evidence.
One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems
We expect that by mixing the user's behaviors across different domains, we can exploit the common knowledge encoded in the pre-trained language model to alleviate the problems of data sparsity and cold start problems.
Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks
In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE).
Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts
In this work, we investigate the ability of state-of-the-art large language models (LLMs) on the task of biomedical abstract simplification, using the publicly available dataset for plain language adaptation of biomedical abstracts (\textbf{PLABA}).
Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion
This paper introduces Laminar, a novel serverless framework based on dispel4py, a parallel stream-based dataflow library.
DeepGATGO: A Hierarchical Pretraining-Based Graph-Attention Model for Automatic Protein Function Prediction
Then, we use GATs to dynamically extract the structural information of non-Euclidean data, and learn general features of the label dataset with contrastive learning by constructing positive and negative example samples.
Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation
Our approach is based on a mutual learning strategy that incorporates two modules: the Cross-sample Mutual Attention Module (CMA) and the Omni-Correlation Consistency Module (OCC).
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses it for more efficient exploration and planning.
Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism
In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices.
M$^2$DAR: Multi-View Multi-Scale Driver Action Recognition with Vision Transformer
Ensuring traffic safety and preventing accidents is a critical goal in daily driving, where the advancement of computer vision technologies can be leveraged to achieve this goal.
Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
Ranked #1 on
3D Object Classification
on ModelNet40
The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination
With the launch of ChatGPT, Large Language Models (LLMs) are shaking up our whole society, rapidly altering the way we think, create and live.
DiffuRec: A Diffusion Model for Sequential Recommendation
Mainstream solutions to Sequential Recommendation (SR) represent items with fixed vectors.
Dynamic Local Feature Aggregation for Learning on Point Clouds
Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers.
Generative Modeling in Structural-Hankel Domain for Color Image Inpainting
To better apply the score-based generative model to learn the internal statistical distribution within patches, the large-scale Hankel matrices are finally folded into the higher dimensional tensors for prior learning.
Latent Space Diffusion Models of Cryo-EM Structures
The state-of-the-art method cryoDRGN uses a Variational Autoencoder (VAE) framework to learn a continuous distribution of protein structures from single particle cryo-EM imaging data.
Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning
In traffic signal control, flow-based (optimizing the overall flow) and pressure-based methods (equalizing and alleviating congestion) are commonly used but often considered separately.
FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs
In this paper, we propose a novel CAM weighting scheme, named FD-CAM, to improve both the faithfulness and discriminability of the CAM-based CNN visual explanation.
Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching
The expansion of renewable energy could help realizing the goals of peaking carbon dioxide emissions and carbon neutralization.
Sequentially Optimal Pricing under Informational Robustness
A seller sells an object over time but is uncertain how the buyer learns their willingness-to-pay.
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training
The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications.
Ranked #1 on
Medical Object Detection
on DeepLesion
Variable Augmented Network for Invertible Modality Synthesis-Fusion
As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning.
Improved Lyman Alpha Tomography using Optimized Reconstruction with Constraints on Absorption (ORCA)
In this work, we propose an improved approach to reconstruct the three-dimensional intergalactic medium from observed Lyman-$\alpha$ forest absorption features.
Astrophysics of Galaxies
Interaction between optical pulse and tumor using finite element analysis
As a non-destructive biological tissue imaging technology, photoacoustic imaging has important application value in the field of biomedicine.
Biological Physics
WB-DETR: Transformer-Based Detector Without Backbone
In this paper, we propose WB-DETR (DETR-based detector Without Backbone) to prove that the reliance on CNN features extraction for a transformer-based detector is not necessary.
Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices
We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.
Ranked #4 on
Medical Object Detection
on DeepLesion
MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #8 on
Medical Object Detection
on DeepLesion
