Model Detail
stable-diffusion-3.5-large
—stable-diffusion-3.5-large is an image generation model released by Stability. The model is registered under the text-to-image pipeline tag on Hugging Face, distributed under a other license.
Access is gated on Hugging Face under the other license, which means a manual approval step before weights can be downloaded.
stable-diffusion-3.5-large is best fit for text-to-image generation and creative iteration. It is a less obvious choice for production photography pipelines that need exact reproducibility. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Retraining Seeks Stable Signals
arXiv:2607.15623v1 Announce Type: cross Abstract: Predictive models deployed at scale influence future data, a phenomenon called performativity. And there is always one way to cope: Train the model on new data, deploy it again, and repeat. This process, called retraining or repeated risk minimizatio
Sharp Stability Threshold and Certification for Designing Stable Residual Architectures
arXiv:2607.14576v1 Announce Type: new Abstract: We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity field: $$\|v(x, t)\| \leq c\,\|x\|^q + b, \qquad q \in [0, 1].$$ The thre
Stable Attention Response for Reliable Precipitation Nowcasting
arXiv:2605.13181v2 Announce Type: replace-cross Abstract: Precipitation nowcasting remains challenging due to the highly localized, rapidly evolving, and heterogeneous nature of atmospheric dynamics. Although recent methods increasingly adopt attention-based architectures in both unimodal and multim
Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability
arXiv:2602.11198v2 Announce Type: replace Abstract: Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code. We introduce \textit{AI-assistability} ($\mathcal{AI}$
AMUSE: Anytime Muon with Stable Gradient Evaluation
arXiv:2605.22432v2 Announce Type: replace Abstract: Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimization removes explicit schedules via iterate averaging, and Muon improves the update geometry by
Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
arXiv:2607.10589v1 Announce Type: cross Abstract: In contrast to most studies on neural network approximation theory that characterize results through a single parameter, such as the total number of network parameters, \cite{shen2020deep} pioneered the characterization of approximation rates as a jo
