
Dive into discrete diffusion modeling for text generation, exploring probability distributions, score-based modeling, and practical applications in generative AI that rival GPT-2's capabilities.

Dive into implementing text generation using discrete diffusion modeling, covering implementation details from basic concepts to training scripts for creating GPT-2 competitive models.

Dive into efficient text-to-image generation using PixART-α, exploring fine-tuning techniques, design principles, and practical implementation steps for diffusion transformers.

Dive into the technical architecture and methodology behind Flux, exploring rectified flow transformers, latent diffusion models, and the innovative approaches that led to superior image generation results.

Explore groundbreaking research on autonomous AI systems capable of conducting end-to-end scientific discovery, from generating ideas to writing papers and performing peer reviews in machine learning.

Explore Crystal Graph Convolutional Neural Networks for predicting material properties and their impact on graph neural networks and transformers in materials design.

Explore open-source Diffusers library for fast, high-quality image and video generation. Learn applications in inpainting, editing, and scene composition using diffusion models.

Explore maximal entropy random walk and its implications for quantum mechanics, including Born rule and Bell violation. Gain insights into statistical mechanics and potential new physics applications.

Explore multiscale modelling of convective mixing in porous media, covering pore-scale and large-scale effects, simulations, experiments, and physical models for geophysical subsurface flows.

Explore continuous upscaling methods for multi-scale modeling. Learn about gradual smoothing transformations, upscaling rules for various physical quantities, and applications to steady-state diffusion problems.

Explore challenges and solutions in multimodal AI, from data management to efficient inference. Learn about systems supporting research and productionization in generative video and language models.

Explore the evolution of generative AI, diffusion models, and LLMs with ML scientist Yuri Plotkin as he discusses his upcoming book "The Variational Book" and shares insights on advanced machine learning concepts.

Explore anomalous transport of tracers in active baths, focusing on long-time dynamics, ratchet effects, and unique friction properties in low-dimensional systems.

Explore large deviations in particle movement models, analyzing entropy production and dynamical activity. Discover various phase transitions and their implications for rate function scaling.

Explore single-file transport and bath-tracer correlations in confined systems, focusing on the Symmetric Exclusion Process and its applications to non-equilibrium situations.

Explore universal exponential tails in diffusing particle packets, extending large deviation theory for continuous time random walks and uncovering general behaviors in transport phenomena.

Explore stochastic resetting in dynamical processes, its impact on system behavior, and applications in chemical reactions and search processes.

Explore Brownian motion near interfaces using experimental, theoretical, and numerical methods. Analyze microparticle trajectories, probability densities, and non-Gaussian behavior to infer nanoscale properties.

Explore yielding transitions in soft jammed materials under oscillatory shear, examining microscopic dynamics, shear banding, and cooperative rearrangements in plastic events.

Explore privacy-preserving synthetic image generation using diffusion models. Learn techniques for fine-tuning pre-trained models to achieve state-of-the-art results on CIFAR-10 and Camelyon17 datasets.

Explore efficient techniques for extracting training images from diffusion models, addressing privacy concerns and copyright issues while uncovering insights into image duplication and template copying.