reconstruction loss

AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction AAAI 2026 A Reproduction Study: The Kernel PCA Interpretation of Self-Attention Fails Under Scrutiny ACL 2025 Drafting and Revision: Advancing High-Fidelity Video Inpainting IJCAI 2025 Enforcing Idempotency in Neural Networks ICML 2025 Learning Phonetic Context-Dependent Viseme for Enhancing Speech-Driven 3D Facial Animation Interspeech 2025 MPPQ: Enhancing Post-Training Quantization for LLMs via Mixed Supervision, Proxy Rounding, and Pre-Searching IJCAI 2025 GRIT: GAN Residuals for Paired Image-to-Image Translation WACV 2024 Learning Low-Rank Latent Spaces With Simple Deterministic Autoencoder: Theoretical and Empirical Insights WACV 2024 Membership Inference Attacks on Diffusion Models via Quantile Regression ICML 2024 PFGS: High Fidelity Point Cloud Rendering via Feature Splatting ECCV 2024 Test-Time Dynamic Image Fusion NeurIPS 2024 Understanding and Leveraging the Learning Phases of Neural Networks AAAI 2024 Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images ICCV 2023 Explicitly Minimizing the Blur Error of Variational Autoencoders ICLR 2023 Overlooked Implications of the Reconstruction Loss for VAE Disentanglement IJCAI 2023 Resilient Binary Neural Network AAAI 2023 Where Did I Come From? Origin Attribution of AI-Generated Images NeurIPS 2023 Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement CVPR 2022 Unlabeled Data Help: Minimax Analysis and Adversarial Robustness AISTATS 2022 Dynamic Memory based Attention Network for Sequential Recommendation AAAI 2021 Speech SimCLR: Combining Contrastive and Reconstruction Objective for Self-Supervised Speech Representation Learning Interspeech 2021 Unsupervised anomaly detection with adversarial mirrored autoencoders UAI 2021 Adversarial Learning of Privacy-Preserving and Task-Oriented Representations AAAI 2020 MAST: A Memory-Augmented Self-Supervised Tracker CVPR 2020 Old Is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm CVPR 2020