Tootfinder

I try to protect my garden. Like many gardens there are vermin - such as rats - that damage, even destroy, the beauty and use of my garden.
I offer no excuses when I remove those vermin from my garden, usually by killing them.
I do have some sympathy for them should the traps not finish the job and they squeak in alarm as I approach to take their lives. But those squeaks do not deter me.
Our world, our nation, our neighborhoods are gardens. There are people who undermine …

GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning
Evgeny Alves Limarenko, Anastasiia Alexandrovna Studenikina
https://arxiv.org/abs/2509.07252

GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning
In multi-task learning (MTL), gradient conflict poses a significant challenge. Effective methods for addressing this problem, including PCGrad, CAGrad, and GradNorm, in their original implementations are computationally demanding, which significantly limits their application in modern large models and transformers. We propose Gradient Conductor (GCond), a method that builds upon PCGrad principles by combining them with gradient accumulation and an adaptive arbitration mechanism. We evaluated GC…

What an epic list.
#degrassi

Pam Bondi fired him for prosecuting January 6 rioters. He’d do it again: ‘it’s about justice’ | US Capitol attack | The Guardian
https://www.theguardian.com/us-news/2025/aug/10/mike-gordon-trump-administration-january-6

I'm an very excited for a Spider Punk movie but also it will have to be terrible, right?
https://deadline.com/2025/08/spider-punk-animated-feature-daniel-kaluuya-ajon-singh-sony-1236478287/

Graph-based Integrated Gradients for Explaining Graph Neural Networks
Lachlan Simpson, Kyle Millar, Adriel Cheng, Cheng-Chew Lim, Hong Gunn Chew
https://arxiv.org/abs/2509.07648

Graph-based Integrated Gradients for Explaining Graph Neural Networks
Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on t…

AI Coding Sucks by Syntax
#webdev #coding

Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
Matias D. Cattaneo, Boris Shigida
https://arxiv.org/abs/2509.08483 https://arxiv.org/pdf/…

Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
We analyze gradient descent with Polyak heavy-ball momentum (HB) whose fixed momentum parameter $β\in (0, 1)$ provides exponential decay of memory. Building on Kovachki and Stuart (2021), we prove that on an exponentially attractive invariant manifold the algorithm is exactly plain gradient descent with a modified loss, provided that the step size $h$ is small enough. Although the modified loss does not admit a closed-form expression, we describe it with arbitrary precision and prove global (f…

D&D 6e Is Here! We Need To Talk About Matt Colville's New RPG by DnD Shorts

#dnd

The Deathbringer RPG Will Change Everything — Here’s Why by Roll For Combat
#ttrpg