Tootfinder

This https://arxiv.org/abs/2312.08616 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

A Generalized Neural Diffusion Framework on Graphs
Recent studies reveal the connection between GNNs and the diffusion process, which motivates many diffusion-based GNNs to be proposed. However, since these two mechanisms are closely related, one fundamental question naturally arises: Is there a general diffusion framework that can formally unify these GNNs? The answer to this question can not only deepen our understanding of the learning process of GNNs, but also may open a new door to design a broad new class of GNNs. In this paper, we propos…

This https://arxiv.org/abs/2311.03326 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Non-convex potential games for finding global solutions to sensor network localization
Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to inves…

This https://arxiv.org/abs/2109.00972 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Weihrauch degree of finding Nash equilibria in multiplayer games
Is there an algorithm that takes a game in normal form as input, and outputs a Nash equilibrium? If the payoffs are integers, the answer is yes, and lot of work has been done in its computational complexity. If the payoffs are permitted to be real numbers, the answer is no, for continuity reasons. It is worthwhile to investigate the precise degree of non-computability (the Weihrauch degree), since knowing the degree entails what other approaches are available (eg, is there a randomized algorith…

Overshown looks to shore up Cowboys’ backups at linebacker https://www.yardbarker.com/nfl/articles/overshown_looks_to_shore_up_cowboys_backups_at_linebacker/s1_17100_40076042

Overshown looks to shore up Cowboys’ backups at linebacker
2024 Roster Review: Backup Linebackers – Part 14 of 17. Click here to view all articles in this series. The Dallas Cowboys did not have a good year regarding their linebackers in 2023. They lost their middle linebacker, and anchor, Leighton Vander Esch five games into the season. Rookie third round pick, DeMarvion Overshown, got hurt in the preseason. He might be able to play in his first NFL game in September. The remaining four players listed at linebacker that served as backups – when Da…

(…)
All plane #games I ever saw for #PC were those complex simulators with complex realistic controls. Those are really cool! But I’m personally not the biggest fan of them, they’re too complex for me and I was never able to even take off on most of them.
Now, I was talking to a friend and he thinks that 95% of people who like #plane games are nerds who love realistic #simulators. He thinks games like the one I used to play don’t exist on #PC because most people wouldn’t play them.
But I absolutely loved that game and I would be super interested in playing something similar!
I’m wanting to get into #gamedev in #Godot and I think developing something like that would be a nice project to learn before doing more complex games.
So: Is he right? Would any of you be interested in a game like that or am I really the only one who likes those games?
Please do comment elaborating on your answer! I’d love to listen to opinions on this (and also if there are already any PC games like that)!
#poll
Interested
Not interested

Language Models as Science Tutors
Alexis Chevalier, Jiayi Geng, Alexander Wettig, Howard Chen, Sebastian Mizera, Toni Annala, Max Jameson Aragon, Arturo Rodr\'iguez Fanlo, Simon Frieder, Simon Machado, Akshara Prabhakar, Ellie Thieu, Jiachen T. Wang, Zirui Wang, Xindi Wu, Mengzhou Xia, Wenhan Jia, Jiatong Yu, Jun-Jie Zhu, Zhiyong Jason Ren, Sanjeev Arora, Danqi Chen

Language Models as Science Tutors
NLP has recently made exciting progress toward training language models (LMs) with strong scientific problem-solving skills. However, model development has not focused on real-life use-cases of LMs for science, including applications in education that require processing long scientific documents. To address this, we introduce TutorEval and TutorChat. TutorEval is a diverse question-answering benchmark consisting of questions about long chapters from STEM textbooks, written by experts. TutorEval…

This https://arxiv.org/abs/2312.08616 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

A Generalized Neural Diffusion Framework on Graphs
Recent studies reveal the connection between GNNs and the diffusion process, which motivates many diffusion-based GNNs to be proposed. However, since these two mechanisms are closely related, one fundamental question naturally arises: Is there a general diffusion framework that can formally unify these GNNs? The answer to this question can not only deepen our understanding of the learning process of GNNs, but also may open a new door to design a broad new class of GNNs. In this paper, we propos…

Language Models as Science Tutors
Alexis Chevalier, Jiayi Geng, Alexander Wettig, Howard Chen, Sebastian Mizera, Toni Annala, Max Jameson Aragon, Arturo Rodr\'iguez Fanlo, Simon Frieder, Simon Machado, Akshara Prabhakar, Ellie Thieu, Jiachen T. Wang, Zirui Wang, Xindi Wu, Mengzhou Xia, Wenhan Jia, Jiatong Yu, Jun-Jie Zhu, Zhiyong Jason Ren, Sanjeev Arora, Danqi Chen

Language Models as Science Tutors
NLP has recently made exciting progress toward training language models (LMs) with strong scientific problem-solving skills. However, model development has not focused on real-life use-cases of LMs for science, including applications in education that require processing long scientific documents. To address this, we introduce TutorEval and TutorChat. TutorEval is a diverse question-answering benchmark consisting of questions about long chapters from STEM textbooks, written by experts. TutorEval…