Tag
ByteDance releases Cola-DLM, a hierarchical continuous latent-space diffusion language model combining a Text VAE with a block-causal Diffusion Transformer, available on Hugging Face with model weights, code, and paper.
This paper introduces DAWN, a latent generative baseline for World-Action Interactive Models (WAIMs) that jointly models scene evolution and action generation through recursive refinement, achieving strong long-horizon planning in autonomous driving scenarios.
The L2P paper introduces a Latent-to-Pixel transfer paradigm that leverages pre-trained latent diffusion models to create efficient pixel-space models capable of 4K generation with minimal training overhead.
This article introduces Prior-Aligned Autoencoders (PAE), a new method for creating diffusion-friendly latent manifolds that achieves state-of-the-art image generation quality while enabling 13x faster training convergence.
This paper introduces TextLDM, a method that adapts visual latent diffusion transformers for language modeling by mapping discrete tokens to continuous latents. It demonstrates that this approach, enhanced by representation alignment, matches GPT-2 performance and unifies visual and text generation architectures.
L2P proposes an efficient transfer paradigm that leverages pre-trained latent diffusion models to build pixel-space diffusion models, enabling high-quality generation with minimal computational overhead and data requirements, and supporting native 4K resolution.
This Hugging Face repository provides workflows and model downloads for Lightricks' LTX-2.3 video generation model, designed for use with ComfyUI, including split models, GGUF versions, and required custom nodes.