Yang Song

SpeeDiff: Scalable Pixel-Anchored End-to-End Latent Diffusion Model CVPR 2026 Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment EMNLP 2025 Granularity-Adaptive Spatial Evidence Tokenization for Video Question Answering AAAI 2025 Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing CVPR 2025 Making Transformer Decoders Better Differentiable Indexers ICLR 2025 Pyramidal Flow Matching for Efficient Video Generative Modeling ICLR 2025 ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability ICLR 2025 RecFlow: An Industrial Full Flow Recommendation Dataset ICLR 2025 Trigger3:Refining Query Correction via Adaptive Model Selector AAAI 2025 Federated Adaptation for Foundation Model-based Recommendations IJCAI 2024 RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance NeurIPS 2024 Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization ICML 2024 Density Ratio Estimation via Infinitesimal Classification AISTATS 2022 GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation ICLR 2022 SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations ICLR 2022 Solving Inverse Problems in Medical Imaging with Score-Based Generative Models ICLR 2022 Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving ICML 2021 Anytime Sampling for Autoregressive Models via Ordered Autoencoding ICLR 2021 CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation NeurIPS 2021 Estimating High Order Gradients of the Data Distribution by Denoising NeurIPS 2021 Imitation with Neural Density Models NeurIPS 2021 Improved Autoregressive Modeling with Distribution Smoothing ICLR 2021 Learning Energy-Based Models by Diffusion Recovery Likelihood ICLR 2021 Maximum Likelihood Training of Score-Based Diffusion Models NeurIPS 2021 PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling ACL 2021 Pseudo-Spherical Contrastive Divergence NeurIPS 2021 Score-Based Generative Modeling through Stochastic Differential Equations ICLR 2021 Autoregressive Score Matching NeurIPS 2020 Diversity can be Transferred: Output Diversification for White- and Black-box Attacks NeurIPS 2020 Efficient Learning of Generative Models via Finite-Difference Score Matching NeurIPS 2020 Gaussianization Flows AISTATS 2020 Improved Techniques for Training Score-Based Generative Models NeurIPS 2020 Permutation Invariant Graph Generation via Score-Based Generative Modeling AISTATS 2020 Training Deep Energy-Based Models with f-Divergence Minimization ICML 2020 Efficient Graph Generation with Graph Recurrent Attention Networks NeurIPS 2019 Generative Modeling by Estimating Gradients of the Data Distribution NeurIPS 2019 MintNet: Building Invertible Neural Networks with Masked Convolutions NeurIPS 2019 Sliced Score Matching: A Scalable Approach to Density and Score Estimation UAI 2019 Accelerating Natural Gradient with Higher-Order Invariance ICML 2018 Constructing Unrestricted Adversarial Examples with Generative Models NeurIPS 2018 PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples ICLR 2018 Kernel Bayesian Inference with Posterior Regularization NeurIPS 2016 Stochastic Gradient Geodesic MCMC Methods NeurIPS 2016 Training Deep Neural Networks via Direct Loss Minimization ICML 2016