Tootfinder

arxiv_authors: Arxiv authors (1993-2003)
Scientific collaborations between authors of papers submitted to arxiv.org, under 5 categories: gr-qc, astro-ph, cond-mat, hep-ph, and hep-th categories, spanning January 1993 to April 2003. If an author i co-authored a paper with author j, the graph contains a undirected edge from i to j. If the paper is co-authored by k authors this generates a completely connected (sub)graph on k nodes.
This network has 26197 nodes and 28980 edges.

How about some recent, well, pretty unusual #astronomy papers? Like https://arxiv.org/abs/2507.02162 = Dangerous Questions in Astronomy Education or https://arxiv.org/abs/2508.19984 = Communicating astrobiology and the search for life elsewhere: speculations and promises of a developing scientific field in newspapers, press releases and papers ... or https://arxiv.org/abs/2508.04718 = Quantum panprotopsychism and a consciousness-centered universe

Wikipedia has •numerous• problems, but it belongs in education.
And right now, per the McSweeney’s OP, it’s a lifeboat of humanity in a sea of slop.
For reference, snapshots of the two articles concerned at the time of this writing:
https://web.archive.org/web/20250923124231/https://www.britannica.com/event/Louisiana-Purchase
https://web.archive.org/web/20250917014942/https://en.wikipedia.org/wiki/Louisiana_Purchase
/end

On the Capacity of Self-Attention
Micah Adler
https://arxiv.org/abs/2509.22840 https://arxiv.org/pdf/2509.22840

On the Capacity of Self-Attention
While self-attention is known to learn relations among tokens, we lack a formal understanding of its capacity: how many distinct relations can a single layer reliably recover for a given budget? To formalize this, we introduce Relational Graph Recognition (RGR), where the key-query channel represents a graph on $m$ items with $m'$ directed edges, and, given a context of items, must recover the neighbors of each item. We measure resources by the total key dimension $D_K = h\,d_k$. Within this …

Communication-Efficient and Interoperable Distributed Learning
Mounssif Krouka, Mehdi Bennis
https://arxiv.org/abs/2509.22823 https://arxiv.org/pdf/2509.22…

Communication-Efficient and Interoperable Distributed Learning
Collaborative learning across heterogeneous model architectures presents significant challenges in ensuring interoperability and preserving privacy. We propose a communication-efficient distributed learning framework that supports model heterogeneity and enables modular composition during inference. To facilitate interoperability, all clients adopt a common fusion-layer output dimension, which permits each model to be partitioned into a personalized base block and a generalized modular block. C…

Localizing Adversarial Attacks To Produces More Imperceptible Noise
Pavan Reddy, Aditya Sanjay Gujral
https://arxiv.org/abs/2509.22710 https://arxiv.org/pd…

Localizing Adversarial Attacks To Produces More Imperceptible Noise
Adversarial attacks in machine learning traditionally focus on global perturbations to input data, yet the potential of localized adversarial noise remains underexplored. This study systematically evaluates localized adversarial attacks across widely-used methods, including FGSM, PGD, and C&W, to quantify their effectiveness, imperceptibility, and computational efficiency. By introducing a binary mask to constrain noise to specific regions, localized attacks achieve significantly lower mean pix…

Score-based Membership Inference on Diffusion Models
Mingxing Rao, Bowen Qu, Daniel Moyer
https://arxiv.org/abs/2509.25003 https://arxiv.org/pdf/2509.25003…

Score-based Membership Inference on Diffusion Models
Membership inference attacks (MIAs) against diffusion models have emerged as a pressing privacy concern, as these models may inadvertently reveal whether a given sample was part of their training set. We present a theoretical and empirical study of score-based MIAs, focusing on the predicted noise vectors that diffusion models learn to approximate. We show that the expected denoiser output points toward a kernel-weighted local mean of nearby training samples, such that its norm encodes proximit…

OAT-FM: Optimal Acceleration Transport for Improved Flow Matching
Angxiao Yue, Anqi Dong, Hongteng Xu
https://arxiv.org/abs/2509.24936 https://arxiv.org/pd…

OAT-FM: Optimal Acceleration Transport for Improved Flow Matching
As a powerful technique in generative modeling, Flow Matching (FM) aims to learn velocity fields from noise to data, which is often explained and implemented as solving Optimal Transport (OT) problems. In this study, we bridge FM and the recent theory of Optimal Acceleration Transport (OAT), developing an improved FM method called OAT-FM and exploring its benefits in both theory and practice. In particular, we demonstrate that the straightening objective hidden in existing OT-based FM methods i…

SourceSplice: Source Selection for Machine Learning Tasks
Ambarish Singh, Romila Pradhan
https://arxiv.org/abs/2507.22186 https://arxiv.org/pdf/2507.22186

SourceSplice: Source Selection for Machine Learning Tasks
Data quality plays a pivotal role in the predictive performance of machine learning (ML) tasks - a challenge amplified by the deluge of data sources available in modern organizations.Prior work in data discovery largely focus on metadata matching, semantic similarity or identifying tables that should be joined to answer a particular query, but do not consider source quality for high performance of the downstream ML task.This paper addresses the problem of determining the best subset of data sou…