Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@NFL@darktundra.xyz
2025-07-18 03:11:29

NFLPA executive director Lloyd Howell steps down amid conflict of interest, collusion controversies

cbssports.com/nfl/news/nflpa-e

@metacurity@infosec.exchange
2025-10-17 08:42:44

bleepingcomputer.com/news/secu
Auction giant Sotheby’s says data breach exposed financial information

@pbloem@sigmoid.social
2025-07-18 09:25:22

Now out in #TMLR:
🍇 GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks 🍇
There's lots of work on sampling subgraphs for GNNs, but relatively little on making this sampling process _adaptive_. That is, learning to select the data from the graph that is relevant for your task.
We introduce an RL-based and a GFLowNet-based sampler and show that the approach perf…

A diagram of the GRAPES pipeline. It shows a subgraph being sampled in two steps and being fed to a GNN, with a blue line showing the learning signal. The caption reads Figure 1: Overview of GRAPES. First, GRAPES processes a target node (green) by computing node inclusion probabilities on its 1-hop neighbors (shown by node color shade) with a sampling GNN. Given these probabilities, GRAPES samples k nodes. Then, GRAPES repeats this process over nodes in the 2-hop neighborhood. We pass the sampl…
A results table for node classification on heterophilious graphs. Table 2: F1-scores (%) for different sampling methods trained on heterophilous graphs for a batch size of 256, and a sample size of 256 per layer. We report the mean and standard deviation over 10 runs. The best values among the sampling baselines (all except GAS) are in bold, and the second best are underlined. MC stands for multi-class and ML stands for multi-label classification. OOM indicates out of memory.
Performance of samples vs sampling size showing that GRAPES generally performs well across sample sizes, while other samplers often show more variance across sample sizes. The caption reads Figure 4: Comparative analysis of classification accuracy across different sampling sizes for sampling baseline
and GRAPES. We repeated each experiment five times: The shaded regions show the 95% confidence intervals.
A diagrammatic illustration of a graph classification task used in one of the theorems. The caption reads Figure 9: An example of a graph for Theorem 1 with eight nodes. Red edges belong to E1, features xi and labels yi are shown beside every node. For nodes v1 and v2 we show the edge e12 as an example. As shown, the label of each node is the second feature of its neighbor, where a red edge connects them. The edge homophily ratio is h=12/28 = 0.43.
@ErikJonker@mastodon.social
2025-08-17 18:26:24

A predictable scenario tomorrow is that Trump will repeat Putin’s “offer” which is unacceptable for Ukraine as everybody knows beforehand, but what is then the next step? Diplomats from the EU are no doubt frantically preparing next steps. The worst thing that can happen is that Trump starts distancing himself from Ukraine and Europe with regard to this war. That is simply too early, Europe is not ready for that, it will be interesting to see how everything develops…

@azonenberg@ioc.exchange
2025-10-18 04:41:06

PIC12F683 just has a few traces of dielectric and a few vias left before it's fully stripped to substrate.
Surprisingly, poly still seems fully intact. I'm not sure if any of my cleaning steps at the end will remove it, but it's quite firmly stuck down and I haven't seen *any* of it floating free yet. Some of the tungsten contacts have come off, which doesn't surprise me at all.
Now that all the oxide over the poly is gone the poly images are even sharper, alt…

SRAM address decode circuitry showing poly and oxide over substrate, with colorful interference fringes in incompletely etched areas
Random logic with slightly blurred contacts and very clearly focused poly/active regions
@qurlyjoe@mstdn.social
2025-10-18 04:28:48

I mean, there’s tons of people talking here about all the shit that’s going down in the world. Sometimes you just need a break from it. Ideally, you’d put down your phone, or tablet, or turn away from your desk, and go do something, something outdoors, maybe. But some of you can’t do that, for reasons, so that’s where the shitposters come in. At least, if you can’t get away entirely, go look at something stupid or amusing or interesting for a bit. Get that blood pressure down, ffs.

@NFL@darktundra.xyz
2025-07-18 03:01:35

NFLPA executive director Lloyd Howell steps down, effective immediately nytimes.com/athletic/6501428/2

@stiefkind@mastodon.social
2025-10-18 07:43:17

Gesellschaft hat kein Interesse an korrekter und exakter Wortwahl. Politischen Blendern gefällt das. #justthinkin

@arXiv_csAI_bot@mastoxiv.page
2025-09-18 07:40:11

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary
arxiv.org/abs/2509.13334

@stiefkind@mastodon.social
2025-08-18 15:12:40

Progrock listeners should be aware of Steven Wilson and/or his band Porcupine Tree (which is probably the best known of all his music activities). Here I have an interesting and entertaining discussion with Steven Wilson about music in general and his musical career in particular. Enjoy: youtube.com/watch?v=jOmpyJUPHpg