Pith. sign in

REVIEW 5 cited by

Optimizing the Latent Space of Generative Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1707.05776 v2 pith:VKG4BDTQ submitted 2017-07-18 stat.ML cs.CVcs.LG

Piotr Bojanowski , Armand Joulin , David Lopez-Paz , Arthur Szlam This is my paper · ORCID
classification stat.MLcs.CVcs.LG
keywords adversarialgansgenerativenetworksoptimizationconvolutionaldeepdiscriminator
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images. In most successful applications, GAN models share two common aspects: solving a challenging saddle point optimization problem, interpreted as an adversarial game between a generator and a discriminator functions; and parameterizing the generator and the discriminator as deep convolutional neural networks. The goal of this paper is to disentangle the contribution of these two factors to the success of GANs. In particular, we introduce Generative Latent Optimization (GLO), a framework to train deep convolutional generators using simple reconstruction losses. Throughout a variety of experiments, we show that GLO enjoys many of the desirable properties of GANs: synthesizing visually-appealing samples, interpolating meaningfully between samples, and performing linear arithmetic with noise vectors; all of this without the adversarial optimization scheme.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CodePhys: Robust Video-based Remote Physiological Measurement through Latent Codebook Querying

    cs.CV 2025-02 conditional novelty 6.0 of 10

    CodePhys casts remote heart-rate measurement as a code query task: a video encoder produces features matched to a learned codebook of clean PPG waveforms, and a pre-trained decoder reconstructs the pulse.

  2. Soft-Constrained Optimization of Latent Space in Variational Autoencoders

    cs.LG 2026-07 conditional novelty 5.0 of 10

    An entropy soft-constraint raises VAE latent capacity and a weight filter prunes unused dimensions, improving activation and FactorVAE scores on dSprites and cutting MNIST latent dim from 10 to 2.

  3. Predicting 3D structure by latent posterior sampling

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    A two-stage method trains NeRF latents then a diffusion prior to sample posteriors for 3D reconstruction from varied observations including single-view, multi-view, noisy, sparse pixels, and sparse depth.

  4. ChatSR: Multimodal Large Language Models for Scientific Formula Discovery

    cs.AI 2024-06 unverdicted novelty 5.0 of 10

    ChatSR aligns scientific data encoders with LLMs to produce formulas that fit data and satisfy explicit priors, reporting SOTA results on 13 symbolic regression benchmarks plus zero-shot handling of unseen prior types.

  5. NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)

    cs.CV 2022-10 unverdicted novelty 2.0 of 10

    A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.

Pith tools