Tootfinder

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/6]:
- Towards Attributions of Input Variables in a Coalition
Xinhao Zheng, Huiqi Deng, Quanshi Zhang
https://arxiv.org/abs/2309.13411
- Knee or ROC
Veronica Wendt, Jacob Steiner, Byunggu Yu, Caleb Kelly, Justin Kim
https://arxiv.org/abs/2401.07390
- Rethinking Disentanglement under Dependent Factors of Variation
Antonio Almud\'evar, Alfonso Ortega
https://arxiv.org/abs/2408.07016 https://mastoxiv.page/@arXiv_csLG_bot/112959235461894530
- Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
Etrit Haxholli, Yeti Z. Gurbuz, Ogul Can, Eli Waxman
https://arxiv.org/abs/2411.00759 https://mastoxiv.page/@arXiv_csLG_bot/113423933393275133
- Predicting Subway Passenger Flows under Incident Situation with Causality
Xiannan Huang, Shuhan Qiu, Quan Yuan, Chao Yang
https://arxiv.org/abs/2412.06871 https://mastoxiv.page/@arXiv_csLG_bot/113632934357523592
- Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling
Paul Joe Maliakel, Shashikant Ilager, Ivona Brandic
https://arxiv.org/abs/2501.08219 https://mastoxiv.page/@arXiv_csLG_bot/113831081884570770
- Universality of Benign Overfitting in Binary Linear Classification
Ichiro Hashimoto, Stanislav Volgushev, Piotr Zwiernik
https://arxiv.org/abs/2501.10538 https://mastoxiv.page/@arXiv_csLG_bot/113872351652969955
- Safe Reinforcement Learning for Real-World Engine Control
Julian Bedei, Lucas Koch, Kevin Badalian, Alexander Winkler, Patrick Schaber, Jakob Andert
https://arxiv.org/abs/2501.16613 https://mastoxiv.page/@arXiv_csLG_bot/113910356206562660
- A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
Roman Tarasov, Petr Mokrov, Milena Gazdieva, Evgeny Burnaev, Alexander Korotin
https://arxiv.org/abs/2502.01310
- Improving the Convergence of Private Shuffled Gradient Methods with Public Data
Shuli Jiang, Pranay Sharma, Zhiwei Steven Wu, Gauri Joshi
https://arxiv.org/abs/2502.03652 https://mastoxiv.page/@arXiv_csLG_bot/113961314098841096
- Using the Path of Least Resistance to Explain Deep Networks
Sina Salek, Joseph Enguehard
https://arxiv.org/abs/2502.12108 https://mastoxiv.page/@arXiv_csLG_bot/114023706252106865
- Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen, Jan-Jakob Sonke, Efstratios Gavves
https://arxiv.org/abs/2502.17028 https://mastoxiv.page/@arXiv_csLG_bot/114063477202397951
- Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
Sharan Vaswani, Reza Babanezhad
https://arxiv.org/abs/2503.00229 https://mastoxiv.page/@arXiv_csLG_bot/114103018985567633
- Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
Yan Li, Zhenyu Zhang, Zhengang Wang, Pengfei Chen, Pengfei Zheng
https://arxiv.org/abs/2503.04398 https://mastoxiv.page/@arXiv_csLG_bot/114120014622063602
- A Survey on Federated Fine-tuning of Large Language Models
Wu, Tian, Li, Sun, Tam, Zhou, Liao, Xiong, Guo, Li, Xu
https://arxiv.org/abs/2503.12016 https://mastoxiv.page/@arXiv_csLG_bot/114182234054681647
- Towards Trustworthy GUI Agents: A Survey
Yucheng Shi, Wenhao Yu, Jingyuan Huang, Wenlin Yao, Wenhu Chen, Ninghao Liu
https://arxiv.org/abs/2503.23434 https://mastoxiv.page/@arXiv_csLG_bot/114263024618476521
- CONTINA: Confidence Interval for Traffic Demand Prediction with Coverage Guarantee
Chao Yang, Xiannan Huang, Shuhan Qiu, Yan Cheng
https://arxiv.org/abs/2504.13961 https://mastoxiv.page/@arXiv_csLG_bot/114380404041503229
- Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
Nikola Zubi\'c, Davide Scaramuzza
https://arxiv.org/abs/2505.11602 https://mastoxiv.page/@arXiv_csLG_bot/114538965060456498
- RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization
Alonso Urbano, David W. Romero, Max Zimmer, Sebastian Pokutta
https://arxiv.org/abs/2505.13289 https://mastoxiv.page/@arXiv_csLG_bot/114539124884913788
- RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
Yilang Zhang, Bingcong Li, Georgios B. Giannakis
https://arxiv.org/abs/2505.18877 https://mastoxiv.page/@arXiv_csLG_bot/114578778213033886
- SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
Bechler-Speicher, Zerio, Huri, Vestergaard, Gilad-Bachrach, Jess, Bhatt, Sazonovs
https://arxiv.org/abs/2505.19193 https://mastoxiv.page/@arXiv_csLG_bot/114578790124778172
toXiv_bot_toot

This is as good a time as any for a thought experiment.
You're in Nazi Germany. You know about the camps, you know what they do, you see the ash fall, you smell it. People who resist alone are killed, some are sent to the camps too. You're afraid to even talk to people about it for fear that they'll turn you in.
You think back to when the camps were being built. You had all the warning signs, but you didn't know how to interpret them. You could believe it would happen. You thought you'd have a chance to vote him out. You thought there might be another way. You thought maybe things would turn out differently if you just sat tight, kept your head down, kept yourself safe.
You see a family being dragged from their home. You know they will be killed. You want to fight, not just for them but for yourself. You opposed Hitler, and at any point you know you could be on the list... Even if you do nothing.
You wish you could rise up, shoot the SS, open the gates, fight it all. You know you aren't alone, but you don't know how to connect with the people who want the same thing.
Using the knowledge we have now, what should you have done in the preceding months and years to connect, to build a community that would open up all paths of resistance?
There were people who resisted. We know it wasn't enough.
Gun laws in Nazi Germany were very similar to US laws in that Nazis were largely free to own guns and everyone else was not. Unlike the US, where "others" have historically controlled using the fear that they might be randomly executed, Germany did codify it. Red flag laws were one more step in the US towards that codification, and there will be more.
When Nazis were taking away those guns, the social networks didn't exist to make resistance possible for most folks. But some Jews were able to resist.
It wasn't the guns that made the Warsaw Ghetto Uprising possible, though they definitely helped. The Warsaw Ghetto uprising was made possible by labor organizing in the precessing years.
If there were more uprisings like that, the Holocaust could have been stopped if not prevented. Social networks make resistance possible. Guns are only useful tools to resist authoritarianism *after* you build a community able to support that resistance, and they are only one of many tools made useful by that community.
Getting guns is easy, and not always necessary. Building community is hard. Guns won't keep you safe. Community will.
Single acts of resistance may slow the machine down, but to actually bring down a monster you need to be able to attack more than once. You need a society of resistance. If you are afraid now, build that. Talk to people while it's still safe to do so. Ask them where their red line is. Talk to neighbors. Figure out your network.
Take the steps you need now to keep your neighbors safe, to keep yourself safe.
#USPol

Tell Congress: Oppose H.R. 5103 the misnamed "Safe and Beautiful Act" being pushed by people who have no interest in living in DC themselves, and wouldn't know beauty if they fell over it. (H.R. 5103 is about as beautiful as the Big Beautiful Bill.)
https://docs.go…

Tell Congress: Oppose Safe and Beautiful // Call Toolkit Mar 2026
TELL CONGRESS:Oppose Safe and Beautiful Updated March 24, 2026 Contents Overview 1 Call List of key lawmakers 2 Call List + Script for DC residents 2 Call Script for allies nationwide 5  Overview The U.S. House is currently advancing H.R. 5103, the “Make the District of ...

“Welcome to hell of Jerry Jones”: NFL fans mock Cowboys as rookie Caleb Downs checks out team's Lombardi trophies "like looking at dinosaur bones" https://www.sportskeeda.com/nfl/news-welco

I see Proton are back on Mastodon after leaving in a huff last year after being criticised for praising the fascists running the USA.
Just a reminder their CEO thinks (I’m using the term very loosely here) that Trump and the Republicans will save us from Big Tech.
(They’re right about the corporate Democrats being shit. The solution to that is to flush the toilet, not jump headfirst into the sewer.) @…

Joe Cooper 🇺🇦 🍉 (@swelljoe@mas.to)
Attached: 2 images @protonprivacy@mastodon.social this you? This is either hopelessly naive or irredeemably dishonest. Gail Slater was a lobbyist for those same oligarchs.

An extremely fascinating article (in French with link in reply to machine translation) via @… :
https://todon.nl/@yetiinabox/116282855527740634
I had not yet submitted myself to a deep dive into Thiel's theology, but it's way more interesting than I had imagined, and explains why he would call his company Palantir, which has always seemed a baffling choice to me. Apparently he's read One Piece, and imagines himself to be constructing A World Government?!?
Also I feel I understand a lot of things about Silicon Valley better now including lots of stuff about social network harms & corporate goals/policies. Belief in Girard's theory of mimetic desire (which I'd not encountered before) explains so much of SV founders' behavior and also it being at least partially reflective of reality explains both their success and some of their harms.

Human Traces X ⛩️
人类踪迹 X ⛩️
📷 Pentax MX
🎞️ Lucky SHD 400
If you like my work, Support by buying me a coffee or a roll of film from PayPal #filmphotography

Loose ends:
First loose end: Before El Cheato ran for office in 2016 he was filmed stating that he though he could make money by being president. I clearly remember that video, but I can not find it.
Second loose end: I think I heard el cheato say that the contrived "settlement" of $1.7Billion was set at that amount in order to give one million dollars to each of the January 6 criminals that he pardoned. The numbers seem to support this.
Maybe we need a new, …

In 1975(76?) I went to a fish fry on the shores of Lake Erie just west of Cleveland. A celebration of once again being able to eat the perch from the cleaned up Lake Erie.
What happened (or, more like didn't happen)?
Troubled Lake Erie is being transformed into a vast water research facility