No article text was recorded for this version.
decoupled generative-inference training
Version 1 of 122 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders
- Blog: On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
- Blog: Reweighted Expectation Maximization
- Blog: Tighter Variational Bounds are Not Necessarily Better
- Blog: Task-Free Continual Generation and Representation Learning via Dynamic Expansionable Memory Cluster
- Blog: InfoVAEGAN: Learning Joint Interpretable Representations by Information Maximization and Maximum Likelihood
- Blog: TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-Tuning
- Blog: Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridges
- Blog: Decision-Making with Auto-Encoding Variational Bayes
- Blog: COMPASS: Decoupled Latent Steering for Protein Conformational Transitions
- Blog: Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder
- Blog: Enhancing temporal commonsense understanding using disentangled attention-based method with a hybrid data framework
- Blog: Enhancing Diffusion Models with Text-Encoder Reinforcement Learning
- Blog: Decoupled Finetuning for Domain Generalizable Semantic Segmentation
- Blog: SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation
- Blog: ZSCRGAN: A GAN-based Expectation Maximization Model for Zero-Shot Retrieval of Images from Textual Descriptions
- Blog: Manifold Matching via Deep Metric Learning for Generative Modeling
- Blog: Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
- Blog: Non-stationary Diffusion For Probabilistic Time Series Forecasting
- Blog: Variational Inference and Model Selection with Generalized Evidence Bounds
- Blog: R-Zero: Self-Evolving Reasoning LLM from Zero Data
- Blog: Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
History & citation
Current · Permanent link
- This direction split from Decoupled Two-Stage Latent Generative Modeling (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_decoupled_generative_inference_training_2cfa41c8,
title = {decoupled generative-inference training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-generative-inference-training/rdr_2cfa41c87e0f4452bfe461a94792cd16},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_decoupled_generative_inference_training_2cfa41c8_v1,
title = {decoupled generative-inference training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-generative-inference-training/rdr_2cfa41c87e0f4452bfe461a94792cd16/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}