Tootfinder

A post from the archive 📫:
Debugging threads with the Parallel Stacks window
https://www.poppastring.com/blog/debugging-threads-with-the-parallel-stacks-window

2025 NFL Division Winner Odds: Crucial Week 16 Games Set to Impact Races https://www.foxsports.com/stories/nfl/2025-nfl-division-winner-odds

With Devin Neal and Devaughn Vele out, who steps up for the Saints? https://www.espn.com/nfl/story/_/id/47340863/with-devin-neal-devaughn-vele-steps-new-orleans-saints-running-back-wide-receiver

Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics
Benjamin Sterling, Yousef El-Laham, M\'onica F. Bugallo
https://arxiv.org/abs/2509.14225

Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics
Recent advances in generative artificial intelligence applications have raised new data security concerns. This paper focuses on defending diffusion models against membership inference attacks. This type of attack occurs when the attacker can determine if a certain data point was used to train the model. Although diffusion models are intrinsically more resistant to membership inference attacks than other generative models, they are still susceptible. The defense proposed here utilizes criticall…

Noise-Level Diffusion Guidance: Well Begun is Half Done
Harvey Mannering, Zhiwu Huang, Adam Prugel-Bennett
https://arxiv.org/abs/2509.13936 https://arxiv.o…

Noise-Level Diffusion Guidance: Well Begun is Half Done
Diffusion models have achieved state-of-the-art image generation. However, the random Gaussian noise used to start the diffusion process influences the final output, causing variations in image quality and prompt adherence. Existing noise-level optimization approaches generally rely on extra dataset construction, additional networks, or backpropagation-based optimization, limiting their practicality. In this paper, we propose Noise Level Guidance (NLG), a simple, efficient, and general noise-le…

2025 NFL Power Rankings Week 12: Which Division Leaders Do We Trust? https://www.foxsports.com/stories/nfl/2025-nfl-power-rankings-week-12-which-division-leaders-do-we-trust

Saints' Neal, Vele ruled out Sunday vs. Jets https://www.espn.com/nfl/story/_/id/47339782/saints-devin-neal-devaughn-vele-ruled-jets

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
Jiayi Pan, Jiaming Xu, Yongkang Zhou, Guohao Dai
https://arxiv.org/abs/2509.13848 https://

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
Feature caching has recently emerged as a promising method for diffusion model acceleration. It effectively alleviates the inefficiency problem caused by high computational requirements by caching similar features in the inference process of the diffusion model. In this paper, we analyze existing feature caching methods from the perspective of information utilization, and point out that relying solely on historical information will lead to constrained accuracy and speed performance. And we prop…

Masked Diffusion Models as Energy Minimization
Sitong Chen, Shen Nie, Jiacheng Sun, Zijin Feng, Zhenguo Li, Ji-Rong Wen, Chongxuan Li
https://arxiv.org/abs/2509.13866 https://…

Masked Diffusion Models as Energy Minimization
We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specifically, we prove that three distinct energy formulations--kinetic, conditional kinetic, and geodesic energy--are mathematically equivalent under the structure of MDMs, and that MDMs minimize all three when the mask schedule satisfies a closed-form optimality condition. This unification not only clarifies the theoretical fo…

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
Wenkui Yang, Jie Cao, Junxian Duan, Ran He
https://arxiv.org/abs/2509.13922

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
Diffusion models like Stable Diffusion have become prominent in visual synthesis tasks due to their powerful customization capabilities, which also introduce significant security risks, including deepfakes and copyright infringement. In response, a class of methods known as protective perturbation emerged, which mitigates image misuse by injecting imperceptible adversarial noise. However, purification can remove protective perturbations, thereby exposing images again to the risk of malicious fo…