arXiv Computer Vision
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Sep 24
Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders
The paper introduces LLMAE, a technique that transforms a pretrained decoder-only language model into a continuous text autoencoder by inserting a fixed-length latent bottleneck into its internal activations. Using a 270M Gemma 3 model with structured attention masks, LoRA adaptation, and KL regularization, LLMAE achieves near-perfect reconstruction of text sequences up to 1024 tokens. The authors further show that the resulting latent representation can be leveraged to train a latent text diffusion model for detailed image captioning, demonstrating downstream utility.
arXiv Machine Learning
Jul 31
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
arXiv:2607. 27372v1 Announce Type: new Abstract: The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages.
arXiv Machine Learning
Jun 16
MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
arXiv:2606. 16408v1 Announce Type: new Abstract: We introduce MUNI, an end-to-end multimodal latent diffusion framework for any-to-any generation that unifies subset-conditioned cross-modal generation and unconditional joint sampling through a shared stochastic latent.
arXiv Computer Vision
Oct 2
Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
arXiv:2610.01942v1 Announce Type: new Abstract: Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of...
arXiv Computer Vision
Sep 14
Unified Text-Image Generation with Weakness-Targeted Post-Training
The paper introduces a post‑training approach that enables a single inference process to transition from text reasoning to image synthesis, eliminating the need for explicit modality switching. Using the 14B BAGEL model, the authors demonstrate that targeted post‑training data and reward‑weighted training improve multimodal image generation across four independent T2I benchmarks. The study highlights the benefits of joint text‑image generation and strategic data selection for enhancing T2I performance.
arXiv Machine Learning
Oct 15
Generation of data on discontinuous manifolds via continuous stochastic non-invertible networks
arXiv:2112.09646v2 Announce Type: replace Abstract: The generation of discontinuous distributions is a difficult task for most known frameworks such as generative autoencoders and generative adversar...