Tootfinder

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu
https://arxiv.org/abs/2510.05184

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures and modalities. In this survey, we investigate the representation potentials of foundation models, defined as the latent capacity of their learned representations to capture task-specific information within a single modality while also providing a transferabl…

Ha!
"Synology Reverses Policy Banning Third-Party HDDs After NAS sales plummet"
https://www.guru3d.com/story/synology-reverses-policy-banning-thirdparty-hdds-after-nas-sales-plummet/

Synology Reverses Policy Banning Third-Party HDDs After NAS sales plummet
Synology has backtracked on one of its most unpopular decisions in years. After seeing NAS sales plummet in 2025, the company has decided to lift restrictions that forced users to buy its own Synology hard drives.

Proportional Representation Is the Solution to Gerrymandering
https://jacobin.com/2025/09/proportional-representation-voting-democrats-gerrymandering/

Limited-visibility Cops and Robbers on Hamming graphs
John Jones, William B. Kinnersley
https://arxiv.org/abs/2509.05196 https://arxiv.org/pdf/2509.05196…

Limited-visibility Cops and Robbers on Hamming graphs
In the classic game of Cops and Robbers, a team of cops pursues a robber through a graph. The traditional model of Cops and Robbers operates under the assumption that the cops know the robber's location at all times. Recently, however, there has been growing interest in models wherein the cops have only partial information about the robber's location. In this paper, we study the limited-visibility variant of Cops and Robbers, in which the cops only know the robber's position if some cop is with…

Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
Lee Kezar, Zed Sehyr, Jesse Thomason
https://arxiv.org/abs/2509.04745 https://

Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but it has not been evaluated whether the learned units capture spurious correlations that hinder out-of-vocabulary performance. This work investigates two phonological inductive biases: Parameter Disentanglement, an architectural bias, and Phonological Semi-Sup…

Reversible computations are computations
Cl\'ement Aubert, Jean Krivine
https://arxiv.org/abs/2510.06585 https://arxiv.org/pdf/2510.06585

Reversible computations are computations
Causality serves as an abstract notion of time for concurrent systems. A computation is causal, or simply valid, if each observation of a computation event is preceded by the observation of its causes. The present work establishes that this simple requirement is equally relevant when the occurrence of an event is invertible. We propose a conservative extension of causal models for concurrency that accommodates reversible computations. We first model reversible computations using a symmetric res…

interactome_vidal: Vidal human interactome (2005)
A network of human proteins and their binding interactions. Nodes represent proteins and an edge represents a binding interaction between two proteins, as tested using a high-throughput yeast two-hybrid (Y2H) system.
This network has 3133 nodes and 6726 edges.
Tags: Biological, Protein interactions, Unweighted

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen, Min-Yen Kan, Luu Anh Tuan
https://arxiv.org/abs/2510.06640

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
State Space Models (SSMs) have recently emerged as efficient alternatives to Transformer-Based Models (TBMs) for long-sequence processing, offering linear scaling and lower memory use. Yet, how contextual information flows across layers and tokens in these architectures remains understudied. We present the first unified, token- and layer-level analysis of representation propagation in SSMs and TBMs. Using centered kernel alignment, stability metrics, and probing, we characterize how representat…

montreal: Montreal street gangs (2007)
Network representing relationships between gangs, obtained from Montreal Police’s central intelligence database, spanning 2004 to 2007. Nodes are gangs, and an edge represents some kind of relationship between two gangs (as elicited from interviews with gang members).
This network has 35 nodes and 78 edges.
Tags: Social, Affiliation, Unweighted

interactome_stelzl: Stelzl human interactome (2005)
A network of human proteins and their binding interactions. Nodes represent proteins and an edge represents an interaction between two proteins, as inferred via high-throughput Y2H experiments using bait and prey methodology.
This network has 1706 nodes and 6207 edges.
Tags: Biological, Protein interactions, Unweighted