Jane Street research intern Kavish Kondap built an event-level generative model of US equities market data using autoregressive diffusion, trained on four years of US equities data with each row conta…
A controlled study submitted to arXiv on 9 Sep 2026 found that moderate LoRA ranks are the most efficient setting for diffusion model fine-tuning, with rank 4 achieving the best DDPM FID of 124.1380 o…
A developer launched ArXivMax, a free tool that generates 3Blue1Brown-style video explainers for any arXiv paper using the open-source Manim animation engine, aiming to help users passively consume re…
A new explainer drawing illustrates the geometric principles behind diffusion models, flow matching, and related generative techniques, tracing the lineage from denoising diffusion probabilistic model…
Diffusion generative models are accelerating AI sampling by exploiting hidden low-dimensional structures, with the denoising diffusion implicit model (DDIM) and denoising diffusion probabilistic model…
HoLo-FuSe, a class-conditional diffusion model using a frozen 27-D HSL byte substrate with zero learned parameters, successfully generated cat and dog faces from AFHQ data at 128px resolution on a sin…
A new paper reveals that diffusion models and flow matching models are unified under the geometry of Wasserstein space, where diffusion follows a gradient flow of free energy and flow matching follows…