Yang Song

56

Papers

326

Total Citations

Papers (56)

Learning Semantic Relationships for Better Action Retrieval in Images

Enhancing Job Recommendation through LLM-Based Generative Adversarial Networks

Stochastic Gradient Geodesic MCMC Methods

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation

Kernel Bayesian Inference with Posterior Regularization

NeurIPS 2016arXiv

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study

PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language Models

Interpretable Image Classification via Non-parametric Part Prototype Learning

Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

Can a Large Language Model be a Gaslighter?

PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations

Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction

GrainSpace: A Large-Scale Dataset for Fine-Grained and Domain-Adaptive Recognition of Cereal Grains

HypLiLoc: Towards Effective LiDAR Pose Regression With Hyperbolic Fusion

Locally-Transferred Fisher Vectors for Texture Classification

Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

Improving 3D Object Detection through Progressive Population Based Augmentation

DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition

Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing

Granularity-Adaptive Spatial Evidence Tokenization for Video Question Answering

Trigger3:Refining Query Correction via Adaptive Model Selector

Your Career Path Matters in Person-Job Fit

Decoupled Optimisation for Long-Tailed Visual Recognition

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Fusing Subcategory Probabilities for Texture Classification

Improving the Robustness of Deep Neural Networks via Stability Training

Age Progression/Regression by Conditional Adversarial Autoencoder

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

The INaturalist Species Classification and Detection Dataset

Class-Balanced Loss Based on Effective Number of Samples

Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-Weighting

Exploiting Edge-Oriented Reasoning for 3D Point-Based Scene Graph Analysis

Constructing Unrestricted Adversarial Examples with Generative Models

Generative Modeling by Estimating Gradients of the Data Distribution

MintNet: Building Invertible Neural Networks with Masked Convolutions

Efficient Graph Generation with Graph Recurrent Attention Networks

Diversity can be Transferred: Output Diversification for White- and Black-box Attacks

Autoregressive Score Matching

Improved Techniques for Training Score-Based Generative Models

Efficient Learning of Generative Models via Finite-Difference Score Matching

Maximum Likelihood Training of Score-Based Diffusion Models

Imitation with Neural Density Models

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Pseudo-Spherical Contrastive Divergence

CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

Estimating High Order Gradients of the Data Distribution by Denoising

On the Robustness of Graph Neural Diffusion to Topology Perturbations

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

Training Deep Neural Networks via Direct Loss Minimization

Accelerating Natural Gradient with Higher-Order Invariance