arXiv Computer Vision September 22, 2026 By Xianghong Fang, Wenjie Shu, Tongda Xu, Wenlong Mou, Dehan Kong, Tim G. J. Rudner

Bridging Reconstruction and Generation: A Latent Distribution Perspective on Evaluation and Improvement

Read the original on arXiv Computer Vision →

The paper investigates why reconstruction quality in latent generative models does not always predict generative performance, attributing the issue to a mismatch between encoder-induced and generation-time latent distributions. It introduces Generation‑Aware Reconstruction (GAR), a method that perturbs encoder latents with noise and denoises them through the generative model before decoding, creating a continuous trajectory that reveals how the decoder behaves across latent spaces. The resulting GAR‑FID metric correlates strongly with generation FID, and using intermediate GAR latents for decoder adaptation consistently improves generative quality across different model scales.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

Sep 1

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

arXiv:2608.29335v1 Announce Type: new Abstract: Latent generative models typically follow a two-stage pipeline, training a variational autoencoder for reconstruction and then a generative model on th...

By Guangting Zheng, Yiyuan Zhang, Tao Yang, Yunpeng Chen, Rui Zhu, Jiajun Deng, Yanyong Zhang

diffusion

arXiv Machine Learning

Aug 21

Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details

arXiv:2509. 05441v4 Announce Type: replace-cross Abstract: Latent generative models compress images into learned embeddings prior to synthesis, and the generation quality critically depends on how faithfully these embeddings preserve visual detail.

By Tejaswini Medi, Hsien-Yi Wang, Arianna Rampini, Margret Keuper

rag diffusion nlp

arXiv AI

Jul 21

SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift

arXiv:2607. 18072v1 Announce Type: cross Abstract: Generative models trained on a source domain often produce samples that are poorly aligned with shifted target domains, limiting their effectiveness for target-domain data augmentation.

By Jiaqi Zhu, Xincheng Chen, Yuncheng Wu, Zhaojing Luo, Beng Chin Ooi

diffusion

arXiv Computer Vision

Sep 3

Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

The paper introduces Latent Drift, a generative forecasting framework that predicts slow-evolving neurodegenerative disease progression by learning changes in a compressed semantic representation rather than full-resolution anatomy. It addresses two failure modes—identity collapse and continuous interpolation trap—by removing pixel-level identity from the prediction target and applying Finite Scalar Quantization to suppress high-frequency nuisance fluctuations. Experiments on longitudinal 3D brain MRI demonstrate that Latent Drift outperforms diffusion and autoregressive transformer baselines in both generative fidelity and clinically relevant metrics.

By Yuxiang Feng, Juncheng Wang, Chao Xu, Wenlong Hou, Huihan Wang, Yijie Qian, Yang Liu, Baigui Sun, Yong Liu, Shujun Wang

llms diffusion efficiency

arXiv AI

Aug 12

JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures

arXiv:2602. 17162v3 Announce Type: replace Abstract: Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature".

By Ariel Larey, Elay Dahan, Amit Bleiweiss, Raizy Kellerman, Guy Leib, Omri Nayshool, Dan Ofer, Tal Zinger, Dan Dominissini, Gideon Rechavi, Nicole Bussola, Simon Lee, Shane O'Connell, Dung Hoang, Marissa Wirth, Alexander W. Charney, Nati Daniel, Yoli Shavit

rag diffusion benchmarks safety

arXiv Machine Learning

Jul 3

eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions

arXiv:2607. 01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets.

By Qijun Chen, Shaofan Li

diffusion benchmarks