vae

"Overall, from my tests, this vae produces identical results to original, but at 3x less vram, and at better speed."

"他们没有使用我们在Stable Diffusion或FLUX中习惯的通常的CLIP + VAE + Diffusion设置，而是构建了一个名为NEO-unify的原生统一模型。"

"决定制作我自己的Stable Diffusion……所有这些都在CPU上完成，使用带有bigru编码器的CFG，具有8x4x4潜空间的32x32图像，VAE和Unet的基础通道为128。"

"“让我们把一切都交给扩散模型处理，无论是VAE的KL散度（正则化）还是图像重建（解码器）！”"

"VibeVoice使用7.5 Hz分词器实现了比Encodec高80倍的压缩率，通过下一令牌扩散，能够在单个LLM上下文窗口内合成最多4个说话者、长达90分钟的自然对话，并以3.76的MOS超越了竞争对手。"

"我们基于 VAE 的 2 倍放大器严格在其范围内放大图像，不会产生幻觉，从而提供纯粹的真实源。"

"本文尝试使用微分几何学和机器学习 (VAE) 来量化企业收购 (M&A) 的整合风险。"

"通过使用 VAE，我们从社会、政治、经济和营销数据中构建战略空间的流形，从噪声数据中获得平滑的潜在空间，并在此空间上执行微分几何和控制工程模拟。"

""RAEs consistently outperform VAEs during pretraining across all model scales. Further, during finetuning on high-quality datasets, VAE-based models catastrophically overfit after 64 epochs, while RAE models remain stable through 256 epochs and achieve consistently better performance.""

"Variational autoencoders (VAEs) are known as image generation models, but can also be used for 'image correction tasks' such as inpainting and noise removal."

"The study focuses on the environmental dependence of Type Ia Supernovae in low-metallicity host galaxies."

"The paper is available on ArXiv."