Tootfinder

Clay Parikh does not want to talk about who he is working with inside the White House.
However, in an extraordinary and extensive conversation with TPM, he had a lot to say about many other things,
including his concerns that the “deep state”
and a shadowy “cabal” is influencing our elections. 
“When they say ‘deep state,’ it’s deep and it’s everywhere,”
Parikh said in a phone call late Tuesday evening. 
Parikh, who, according to court documents unsealed th…

Meet the ‘Cabal’-Hating ‘Special Government Employee’ Involved in the Fulton County FBI Raid
Clay Parikh unloaded in a nearly two hour conversation with TPM.

Kimi Onoda, Japan's new Minister of State for Economic Security, is a 43 year old half-Irish ex-game industry PR femcel with an extensive history of defending her exclusive attraction to anime boys on twitter

NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization
Gaorui Zhang, Zhizhang Yuan, Jialan Yang, Junru Chen, Li Meng, Yang Yang
https://arxiv.org/abs/2512.09524 https://arxiv.org/pdf/2512.09524 https://arxiv.org/html/2512.09524
arXiv:2512.09524v1 Announce Type: new
Abstract: Neural decoding, a critical component of Brain-Computer Interface (BCI), has recently attracted increasing research interest. Previous research has focused on leveraging signal processing and deep learning methods to enhance neural decoding performance. However, the in-depth exploration of model architectures remains underexplored, despite its proven effectiveness in other tasks such as energy forecasting and image classification. In this study, we propose NeuroSketch, an effective framework for neural decoding via systematic architecture optimization. Starting with the basic architecture study, we find that CNN-2D outperforms other architectures in neural decoding tasks and explore its effectiveness from temporal and spatial perspectives. Building on this, we optimize the architecture from macro- to micro-level, achieving improvements in performance at each step. The exploration process and model validations take over 5,000 experiments spanning three distinct modalities (visual, auditory, and speech), three types of brain signals (EEG, SEEG, and ECoG), and eight diverse decoding tasks. Experimental results indicate that NeuroSketch achieves state-of-the-art (SOTA) performance across all evaluated datasets, positioning it as a powerful tool for neural decoding. Our code and scripts are available at https://github.com/Galaxy-Dawn/NeuroSketch.
toXiv_bot_toot

Omnicom's DM9 returned three Cannes awards after a NC state senator and CNN Brazil found the company had used AI to manipulate their content and used it for ads (Emmanuel Felton/Washington Post)
https://www.washingtonpost.com/nation/2025/11/30/deep-fake-whirlo…

Deepfake of North Carolina lawmaker used in award-winning Whirlpool video
North Carolina state Sen. DeAndrea Salvador discovered her 2018 TED Talk had been altered by an ad agency working for Whirlpool in Brazil, leading to a lawsuit.

The Secret History of the Deep State (James Rosen/New York Times)
https://www.nytimes.com/2026/02/08/opinion/trump-nixon-watergate-radford.html?unlocked_article_code=1.KlA.jyVZ.dyIlbsiUt8oq&smid=nytcore-ios-share
http://www.memeorandum.com/260208/p22#a260208p22

Omnicom's DM9 returned three Cannes awards after a NC state senator and CNN Brazil found the company had used AI to manipulate their content and used it for ads (Emmanuel Felton/Washington Post)
https://www.washingtonpost.com/nation/2025/11/30/deep-fake-whirlo…

Deepfake of North Carolina lawmaker used in award-winning Whirlpool video
North Carolina state Sen. DeAndrea Salvador discovered her 2018 TED Talk had been altered by an ad agency working for Whirlpool in Brazil, leading to a lawsuit.

How soon before LLMs replace the laborers?
Age of the ‘scam state’: how an illicit, multibillion-dollar industry has taken root in south-east Asia
https://www.theguardian.com/technology/2025/dec/02/sc…

How soon before LLMs replace the laborers?
Age of the ‘scam state’: how an illicit, multibillion-dollar industry has taken root in south-east Asia
https://www.theguardian.com/technology/2025/dec/02/sc…

Weekend #Plankton Factoid 🦠🦐
Some calanoid copepods, including Calanus finmarchicus, spend 6-8 months of the winter in a dormancy state as juvenile copepodites deep under the thermocline at a depth of 500-1500m which reduces predation and energy use. This depth is determined by interaction of temperature and salinity of the water and the copepod's lipid content of waxy esters. They have …

Geschichte wird von Siegern geschrieben. 🤮
https://www.whitehouse.gov/j6/

January 6: A Date Which Will Live in Infamy
Discover the real January 6 story: peaceful protest turned tragedy, Deep State entrapment, media deception, and President Trump's triumphant pardons restoring justice to patriotic Americans.

If anything, one piece of evidence supporting Liz Truss's thesis about the decline of Britain, is the national indignity of a former Prime Minister appearing on Rumble to rant about the deep state wokes.
(She *was* Prime Minister, there are citations for this on Wikipedia.)

"the Journal argued that the recent decision by the Jim Beam distillery to halt production at its Claremont, Kentucky facility for all of 2026 can be chalked up to Trump's tariffs."
Trump is actively causing 'harm' to this deep-red state's key industry: WSJ - Alternet.org
https://www.alternet.org/trump-harm-red-state/

Tech analyst Dan Wang reflects on the Chinese Communist Party vs. Silicon Valley, AI and manufacturing, and how China and the US are building the future (Dan Wang)
https://danwang.co/2025-letter/

2025 letter | Dan Wang
Corgis, compute, Cold War; Ecclesiastes; ties; Stendhal; humor; Pascal's Wager; deep infrastructure; Germanic obedience; Texas State Fair

deep state humiliation ritual where they make u put white neurospicy late 30s queerdo in ur bio

https://assumptionblanket.blogspot.com/2026/01/i-just-got-laid-off-but-this-post-isnt.html?m=1

I just got laid off. But this post isn’t what you think.
OK, deep breath, here we go. Yesterday, January 12, 2026, I got laid off from my job with the State of Minnesota due to budget constraints...

Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
Yuri Calleo
https://arxiv.org/abs/2512.17696 https://arxiv.org/pdf/2512.17696 https://arxiv.org/html/2512.17696
arXiv:2512.17696v1 Announce Type: new
Abstract: The modeling of high-dimensional spatio-temporal processes presents a fundamental dichotomy between the probabilistic rigor of classical geostatistics and the flexible, high-capacity representations of deep learning. While Gaussian processes offer theoretical consistency and exact uncertainty quantification, their prohibitive computational scaling renders them impractical for massive sensor networks. Conversely, modern transformer architectures excel at sequence modeling but inherently lack a geometric inductive bias, treating spatial sensors as permutation-invariant tokens without a native understanding of distance. In this work, we propose a spatially-informed transformer, a hybrid architecture that injects a geostatistical inductive bias directly into the self-attention mechanism via a learnable covariance kernel. By formally decomposing the attention structure into a stationary physical prior and a non-stationary data-driven residual, we impose a soft topological constraint that favors spatially proximal interactions while retaining the capacity to model complex dynamics. We demonstrate the phenomenon of ``Deep Variography'', where the network successfully recovers the true spatial decay parameters of the underlying process end-to-end via backpropagation. Extensive experiments on synthetic Gaussian random fields and real-world traffic benchmarks confirm that our method outperforms state-of-the-art graph neural networks. Furthermore, rigorous statistical validation confirms that the proposed method delivers not only superior predictive accuracy but also well-calibrated probabilistic forecasts, effectively bridging the gap between physics-aware modeling and data-driven learning.
toXiv_bot_toot

"Despite the generally strong support for democracy, there was an equally strong desire for radical change, with more people in most countries thinking the system was rigged in favour of the rich and powerful rather than working for everyone."
What? Do ordinary mortals think the neoliberal cosnsenus has failed us? How can this be? Look at all the wonderful things the billionaires have developed for us!

"Despite the generally strong support for democracy, there was an equally strong desire for radical change, with more people in most countries thinking the system was rigged in favour of the rich and powerful rather than working for everyone."
What? Do ordinary mortals think the neoliberal cosnsenus has failed us? How can this be? Look at all the wonderful things the billionaires have developed for us!

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- The Diffusion Duality
Sahoo, Deschenaux, Gokaslan, Wang, Chiu, Kuleshov
https://arxiv.org/abs/2506.10892 https://mastoxiv.page/@arXiv_csLG_bot/114675526577078472
- Multimodal Representation Learning and Fusion
Jin, Ge, Xie, Luo, Song, Bi, Liang, Guan, Yeong, Song, Hao
https://arxiv.org/abs/2506.20494 https://mastoxiv.page/@arXiv_csLG_bot/114749113025183688
- The kernel of graph indices for vector search
Mariano Tepper, Ted Willke
https://arxiv.org/abs/2506.20584 https://mastoxiv.page/@arXiv_csLG_bot/114749118923266356
- OptScale: Probabilistic Optimality for Inference-time Scaling
Youkang Wang, Jian Wang, Rubing Chen, Xiao-Yong Wei
https://arxiv.org/abs/2506.22376 https://mastoxiv.page/@arXiv_csLG_bot/114771735361664528
- Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods
Fabian Akkerman, Julien Ferry, Christian Artigues, Emmanuel Hebrard, Thibaut Vidal
https://arxiv.org/abs/2507.18242 https://mastoxiv.page/@arXiv_csLG_bot/114913322736512937
- MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking
Runwen Hu, Peilin Chen, Keyan Ding, Shiqi Wang
https://arxiv.org/abs/2508.17702 https://mastoxiv.page/@arXiv_csLG_bot/115095014405732247
- Dual-Distilled Heterogeneous Federated Learning with Adaptive Margins for Trainable Global Protot...
Fatema Siddika, Md Anwar Hossen, Wensheng Zhang, Anuj Sharma, Juan Pablo Mu\~noz, Ali Jannesari
https://arxiv.org/abs/2508.19009 https://mastoxiv.page/@arXiv_csLG_bot/115100269482762688
- STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
Gary Simethy, Daniel Ortiz-Arroyo, Petar Durdevic
https://arxiv.org/abs/2508.19011 https://mastoxiv.page/@arXiv_csLG_bot/115100270137397046
- EEGDM: Learning EEG Representation with Latent Diffusion Model
Shaocong Wang, Tong Liu, Yihan Li, Ming Li, Kairui Wen, Pei Yang, Wenqi Ji, Minjing Yu, Yong-Jin Liu
https://arxiv.org/abs/2508.20705 https://mastoxiv.page/@arXiv_csLG_bot/115111565155687451
- Data-Free Continual Learning of Server Models in Model-Heterogeneous Cloud-Device Collaboration
Xiao Zhang, Zengzhe Chen, Yuan Yuan, Yifei Zou, Fuzhen Zhuang, Wenyu Jiao, Yuke Wang, Dongxiao Yu
https://arxiv.org/abs/2509.25977 https://mastoxiv.page/@arXiv_csLG_bot/115298721327100391
- Fine-Tuning Masked Diffusion for Provable Self-Correction
Jaeyeon Kim, Seunggeun Kim, Taekyun Lee, David Z. Pan, Hyeji Kim, Sham Kakade, Sitan Chen
https://arxiv.org/abs/2510.01384 https://mastoxiv.page/@arXiv_csLG_bot/115309690976554356
- A Generic Machine Learning Framework for Radio Frequency Fingerprinting
Alex Hiles, Bashar I. Ahmad
https://arxiv.org/abs/2510.09775 https://mastoxiv.page/@arXiv_csLG_bot/115372387779061015
- ASecond-Order SpikingSSM for Wearables
Kartikay Agrawal, Abhijeet Vikram, Vedant Sharma, Vaishnavi Nagabhushana, Ayon Borthakur
https://arxiv.org/abs/2510.14386 https://mastoxiv.page/@arXiv_csLG_bot/115389079527543821
- Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
Heming Zou, Yixiu Mao, Yun Qu, Qi Wang, Xiangyang Ji
https://arxiv.org/abs/2510.16882 https://mastoxiv.page/@arXiv_csLG_bot/115412243355962887
- Seeing Structural Failure Before it Happens: An Image-Based Physics-Informed Neural Network (PINN...
Omer Jauhar Khan, Sudais Khan, Hafeez Anwar, Shahzeb Khan, Shams Ul Arifeen
https://arxiv.org/abs/2510.23117 https://mastoxiv.page/@arXiv_csLG_bot/115451891042176876
- Training Deep Physics-Informed Kolmogorov-Arnold Networks
Spyros Rigas, Fotios Anagnostopoulos, Michalis Papachristou, Georgios Alexandridis
https://arxiv.org/abs/2510.23501 https://mastoxiv.page/@arXiv_csLG_bot/115451942159737549
- Semi-Supervised Preference Optimization with Limited Feedback
Seonggyun Lee, Sungjun Lim, Seojin Park, Soeun Cheon, Kyungwoo Song
https://arxiv.org/abs/2511.00040 https://mastoxiv.page/@arXiv_csLG_bot/115490555013124989
- Towards Causal Market Simulators
Dennis Thumm, Luis Ontaneda Mijares
https://arxiv.org/abs/2511.04469 https://mastoxiv.page/@arXiv_csLG_bot/115507943827841017
- Incremental Generation is Necessary and Sufficient for Universality in Flow-Based Modelling
Hossein Rouhvarzi, Anastasis Kratsios
https://arxiv.org/abs/2511.09902 https://mastoxiv.page/@arXiv_csLG_bot/115547587245365920
- Optimizing Mixture of Block Attention
Guangxuan Xiao, Junxian Guo, Kasra Mazaheri, Song Han
https://arxiv.org/abs/2511.11571 https://mastoxiv.page/@arXiv_csLG_bot/115564541392410174
- Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs
Shasha Zhou, Mingyu Huang, Jack Cole, Charles Britton, Ming Yin, Jan Wolber, Ke Li
https://arxiv.org/abs/2511.12817 https://mastoxiv.page/@arXiv_csLG_bot/115570877730326947
toXiv_bot_toot