KRONOS: Autoregressive latent diffusion for 3D molecule generation
Researchers introduce KRONOS, a latent autoregressive diffusion framework for 3D molecule generation that operates in the latent space of a pre-trained autoencoder. It addresses the limitation of diffusion models requiring molecular size a priori, supporting variable-length generation and context conditioning.
Entities
Related
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Researchers introduced ARDY, a streaming generation framework that enables real-time synthesis of 3D human motions with text and kinematic control, bridging the gap between offline precision and online speed. The method addresses limitations in existing online approaches regarding controllability and complex text semantics.
ELSA3D introduces elastic semantic anchoring for unified 3D understanding and generation
ELSA3D is a unified 3D foundation model that uses elastic semantic anchoring to jointly structure language and geometric reasoning across matched abstraction scales. It addresses the collapse of coarse and fine details in existing models that concatenate text and 3D tokens into flat sequences. The approach represents geometry with scale-aware features, enabling more explicit text-3D interaction within a single backbone.
Physics-constrained ML framework accelerates DNS of turbulent reacting flows
Researchers propose a machine learning surrogate that replaces detailed chemical source terms in direct numerical simulation of turbulent reacting flows. The model enforces the second law of thermodynamics as a training constraint to ensure physical consistency and stability.
Paper proposes video generation as general-purpose vision pretraining
A new arXiv paper argues that large-scale text-to-video generation can serve as a general-purpose pretraining paradigm for computer vision, analogous to next-token prediction in NLP. The authors introduce GenCeption, a method that uses a pretrained video generative diffusion backbone for feed-forward visual perception tasks.
Terrain Diffusion: AI generates infinite Minecraft terrain from a single seed
A new AI system called Terrain Diffusion generates infinite, coherent Minecraft terrain from a single seed image. The project, released on Modrinth and GitHub, uses a diffusion model to produce novel terrain that matches the style of the input. The video by Two Minute Papers highlights the method and provides links to the paper and code.