Tootfinder

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization a...
Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
https://arxiv.org/abs/2306.09158
- Sparse, Efficient and Explainable Data Attribution with DualXDA
Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2402.12118 https://mastoxiv.page/@arXiv_csLG_bot/111962593972369958
- HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Sun, Que, {\AA}rrestad, Loncar, Ngadiuba, Luk, Spiropulu
https://arxiv.org/abs/2405.00645 https://mastoxiv.page/@arXiv_csLG_bot/112370274737558603
- On the Identification of Temporally Causal Representation with Instantaneous Dependence
Li, Shen, Zheng, Cai, Song, Gong, Chen, Zhang
https://arxiv.org/abs/2405.15325 https://mastoxiv.page/@arXiv_csLG_bot/112511890051553111
- Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
https://arxiv.org/abs/2405.15877 https://mastoxiv.page/@arXiv_csLG_bot/112517547424098076
- Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
https://arxiv.org/abs/2409.03735 https://mastoxiv.page/@arXiv_csLG_bot/113089789682783135
- Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
https://arxiv.org/abs/2410.06800 https://mastoxiv.page/@arXiv_csLG_bot/113283021321510736
- Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen
https://arxiv.org/abs/2410.18686 https://mastoxiv.page/@arXiv_csLG_bot/113367101100828901
- Fairness via Independence: A (Conditional) Distance Covariance Framework
Ruifan Huang, Haixia Liu
https://arxiv.org/abs/2412.00720 https://mastoxiv.page/@arXiv_csLG_bot/113587817648503815
- Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Simon Frieder, et al.
https://arxiv.org/abs/2412.15184 https://mastoxiv.page/@arXiv_csLG_bot/113683924322164777
- Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
https://arxiv.org/abs/2501.10290 https://mastoxiv.page/@arXiv_csLG_bot/113859392622871057
- Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
https://arxiv.org/abs/2501.10321 https://mastoxiv.page/@arXiv_csLG_bot/113859392688054204
- Regularized Langevin Dynamics for Combinatorial Optimization
Shengyu Feng, Yiming Yang
https://arxiv.org/abs/2502.00277
- Generating Samples to Probe Trained Models
Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil
https://arxiv.org/abs/2502.06658 https://mastoxiv.page/@arXiv_csLG_bot/113984059089245671
- On Agnostic PAC Learning in the Small Error Regime
Julian Asilis, Mikael M{\o}ller H{\o}gsgaard, Grigoris Velegkas
https://arxiv.org/abs/2502.09496 https://mastoxiv.page/@arXiv_csLG_bot/114000974082372598
- Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, Geoffrey Ye Li
https://arxiv.org/abs/2502.10784 https://mastoxiv.page/@arXiv_csLG_bot/114023667639951005
- On the Effect of Sampling Diversity in Scaling LLM Inference
Wang, Liu, Chen, Light, Liu, Chen, Zhang, Cheng
https://arxiv.org/abs/2502.11027 https://mastoxiv.page/@arXiv_csLG_bot/114023688225233656
- How to use score-based diffusion in earth system science: A satellite nowcasting example
Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff
https://arxiv.org/abs/2505.10432 https://mastoxiv.page/@arXiv_csLG_bot/114516300594057680
- PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Christoffer Petersson, Daniel Persson, Jan E. Gerken
https://arxiv.org/abs/2505.17720 https://mastoxiv.page/@arXiv_csLG_bot/114572963019603744
- Train Sparse Autoencoders Efficiently by Utilizing Features Correlation
Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky
https://arxiv.org/abs/2505.22255 https://mastoxiv.page/@arXiv_csLG_bot/114589956040892075
- A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
https://arxiv.org/abs/2506.06486 https://mastoxiv.page/@arXiv_csLG_bot/114658421178857085
toXiv_bot_toot

A century of glaciers melting, condensed into a few seconds. Impressive video: https://www.instagram.com/reel/DQWfDRejcPw/?igsh=Zm51d2Qzb2xtNHM4

Michel Galati on Instagram: "A century of change condensed into a few seconds. In collaboration with @glacionaut I transformed historical and contemporary photographs of Swiss and Austrian glaciers into short AI-animated sequences (Dream Machine by @lumalabsai ). Each clip shows the passage from past to present. The climate has always changed, true, but never this fast. In the past two years alone, Swiss glaciers have lost more than 10% of their total volume (source: Swiss Academy of Sciences). What once took centuries now happens in decades. And yes, the music is The Four Seasons by Vivaldi. An homage to nature, and perhaps a reminder of what we stand to lose. 📍 Photos: @glacionaut 🎥 AI Animation: @flashologo 🗓️ Period: ca. 1875–2024 • 🇮🇹 Un secolo di cambiamento racchiuso in pochi secondi. In collaborazione con @glacionaut, ho trasformato fotografie storiche e contemporanee di alcuni ghiacciai svizzeri e austriaci in brevi sequenze animate con l’intelligenza artificiale (Dream Machine di @lumalabsai). Ogni clip mostra il passaggio dal passato al presente. Il clima è sempre cambiato, è vero, ma mai così rapidamente. Negli ultimi due anni i ghiacciai svizzeri hanno perso oltre il 10% del loro volume (fonte: Swiss Academy of Sciences). Ciò che un tempo accadeva in secoli, oggi avviene in decenni. E sì, la musica è Le Quattro Stagioni di Vivaldi. Un omaggio alla natura e, forse, un promemoria di ciò che rischiamo di perdere. 📍 Foto: @glacionaut 🎥 Animazioni AI: @flashologo 🗓️ Periodo: ca. 1875–2024 • • #ai #dreammachine #ray3 #imagetovideo #glaciers #switzerland #austria #climatchange #history"
44K likes, 814 comments - flashologo on October 28, 2025: "A century of change condensed into a few seconds. In collaboration with @glacionaut I transformed historical and contemporary photographs of Swiss and Austrian glaciers into short AI-animated sequences (Dream Machine by @lumalabsai ). Each clip shows the passage from past to present. The climate has always changed, true, but never this fast. In the past two years alone, Swiss glaciers have lost more than 10% of their total volume (sou…

Now this was a gorgeous cycling loop. Temperature was around freezing but luckily just few wind. As you see, the weather was ace. Clouds and fog stayed in the north 🌞
Also tried Knee warmers, which was just right! A very good buy!
I just need a solution against freezing toes. @… ,I bought neoprene toe warmer! The shoes are just a bit tight then, …

Berlin wagt den ersten Schritt in Richtung Open-Source! 🐧 Die Hauptstadt hat erkannt, dass die jahrzehntelange Abhängigkeit von proprietärer Software nicht nur teuer ist, sondern angesichts geopolitischer Spannungen auch ein Sicherheitsrisiko darstellt.
Zum Artikel: https://heise.de/-11148087

Were Israel to shoot a Western journalist, the journalist would be like “I guess I was Hamas, oh, well, I guess I’ll die.”
I use “journalist”, here, very loosely. @… https://

Assal Rad
Israel is the world’s leading killer of journalists, they killed one of your own, and you still use “Israel says” to try to justify it. What a shameful post.

After #Trump finally crashes and burns (I'm still saying I don't think he makes it to the mid terms, and I think it's more than possible he won't make it to the end of the year) we'll hear a lot of people say, "the system worked!" Today people are already talking about "saving democracy" by fighting back. This will become a big rally cry to vote (for Democrats, specifically), and the complete failure of the system will be held up as the best evidence for even greater investment in it.
I just want to point out that American democracy gave nuclear weapons to a pedophile, who, before being elected was already a well known sexual predator, and who made the campaign promise to commit genocide. He then preceded to commit genocide. And like, I don't care that he's "only" kidnaped and disappeared a few thousand brown people. That's still genocide. Even if you don't kill every member of a targeted group, any attempt to do so is still "committing genocide." Trump said he would commit genocide, then he hired all the "let's go do a race war" guys he could find and *paid* them to go do a race war. And, even now as this deranged monster is crashing out, he is still authorized to use the world's largest nuclear arsenal.
He committed genocide during his first term when his administration separated migrant parents and children, then adopted those children out to other parents. That's technically genocide. The point was to destroy the very people been sending right wing terror squads after.
There was a peaceful hand over of power to a known Russian asset *twice*, and the second time he'd already committed *at least one* act of genocide *and* destroyed cultural heritage sites (oh yeah, he also destroyed indigenous grave sites, in case you forgot, during his first term).
All of this was allowed because the system is set up to protect exactly these types of people, because *exactly* these types of people are *the entire power structure*.
Going back to that system means going back to exactly the system that gave nuclear weapons to a pedophile *TWICE*.
I'm already seeing the attempts to pull people back, the congratulations as we enter the final phase, the belief that getting Trump out will let us all get back to normal. Normal. The normal that lead here in the first place. I can already see the brunch reservations being made. When Trump is over, we will be told we won. We will be told that it's time to go back to sleep.
When they tell you everything worked, everything is better, that we can stop because we won, tell them "fuck you! Never again means never again." Destroy every system that ever gave these people power, that ever protected them from consequences, that ever let them hide what they were doing.
These democrats funded a genocide abroad and laid the groundwork for genocide at home. They protected these predators, for years. The whole power structure is guilty. As these files implicate so many powerful people, they're trying to shove everything back in the box. After all the suffering, after we've finally made it clear that we are the once with the power, only now they're willing to sacrifice Trump to calm us all down.
No, that's a good start but it can't be the end.
Winning can't be enough to quench that rage. Keep it burning. When this is over, let victory fan that anger until every institution that made this possible lies in ashes. Burn it all down and salt the earth. Taking down Trump is a great start, but it's not time to give up until this isn't possible again.
#USPol

Hier, bitte ⤵️
Bevor das nächste Mal wieder alle entsetzt sind über die Zustände im Osten: Das wird nicht besser, wenn denen niemand hilft, die den Rasssismus, die Behindertenfeindlichkeit, die Nazi-Gewalt abkriegen.
Bitte nehmt Euch die paar Minuten.
https://links.potsda.mn/@opferperspekt<…

Große Änderungen beim Jugendschutz in Deutschland! 🔍 Die Bundesländer haben eine weitreichende Reform des Jugendmedienschutz-Staatsvertrags beschlossen, die direkte Auswirkungen auf alle digitalen Geräte haben wird.
Zum Artikel: https://heise.de/-11086704?wt_m…

heise | heise Update vom 21. November 2025: Lesetipps fürs Wochenende
Der wöchentliche Newsletter von heise dieses Mal mit Kreditkartenbetrug, VR-Brillen, Quantenphysik, E-Auto-Akkus und Fotobüchern.
https:/…

Bundeskartellamt verhängt 2025 weniger Bußgelder
Das Bundeskartellamt hat 2025 weniger Bußgelder wegen Kartellverfahren verhängt – deutlich weniger als im Vorjahr.
https://www.heise.de/news/…