Tootfinder

Anthropic details "persona vectors", patterns of activity within an AI model's neural network that control its character traits, such as evil and sycophancy (Anthropic)
https://www.anthropic.com/research/persona-vectors

Persona vectors: Monitoring and controlling character traits in language models
A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior

"Total Victory": Gericht weist Google-Berufung im Epic-Rechtsstreit zurück
Googles Berufung gegen die Jury-Entscheidung im App-Store-Streit mit Epic Games wurde abgewiesen. Nun könnten die Konsequenzen real werden.

Gay lawmaker wants to roll back what was once a major LGBTQ victory. People aren't taking it well. - LGBTQ Nation
https://www.lgbtqnation.com/2025/07/gay-lawmaker-wants-to-roll-back-what-was-once-a-major-lgbtq-victory-people-arent-taking-it-well/

"A tree a minute for 24 hours: the young Victorian forest that was planted in a day"
#Australia #Trees #Environment

DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
Mohammad Hassan Vali, Tom B\"ackstr\"om, Arno Solin
https://arxiv.org/abs/2509.26469 https…

DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also present a space-filling variant (SF-DiVeQ) that assigns to a curve constructed by the lines connecting codewords, resulting in less quantization error and full codebook usage. Both methods train end-to…

Topological Vector Spaces
Pierre Colmez, Wies{\l}awa Nizio{\l}
https://arxiv.org/abs/2509.25981 https://arxiv.org/pdf/2509.25981

Topological Vector Spaces
Motivated by applications to duality theorems for $p$-adic pro-étale cohomology of rigid analytic spaces, we study the category of Topological Vector Spaces in the setting of condensed mathematics. We prove that it contains, as full subcategories, both the category of (topologically) bounded algebraic Vector Spaces and the category of perfect complexes on the Fargues-Fontaine curve. Vector Spaces coming from $p$-adic pro-étale cohomology of smooth partially proper rigid analytic varieties are…

Das #Rezept des Tages:
🌿🍲 Probiert doch mal die vegetarische Variante des herzhaften, ukrainischen Nationalgerichtes #Borschtsch aus! Mit Rote Bete, #Möhren und

Borschtsch: Das ukrainische Nationalgericht in einer vegetarischen Variante
Borschtsch aus der Ukraine ist Immaterielles UNESCO-Welterbe. Probieren Sie das Gericht aus, es ist lecker!

Chirality structure of vector like new physics operators in charged current transitions
Sajawal Zafar, Qazi Maaz Us Salam, Rana Khan, Ishtiaq Ahmed, Rizwan Khalid
https://arxiv.org/abs/2507.23721

Chirality structure of vector like new physics operators in charged current transitions
We investigate the cascade decay $B^{*0}_{s} \rightarrow D_s^-(\rightarrow τ^-\,\barν_τ)\,\ell^{+}\,ν_\ell$ induced by flavor changing charged currents in the context of the Standard Model and in vector-like couplings beyond the Standard Model. We employ the helicity amplitude formalism for analysis and highlight the role of new vector-like couplings in charged current interactions. We find, in particular, that while new left handed chiral-vector like interactions contribute to the branchin…

RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
Han Zhang, Dongfang Zhao
https://arxiv.org/abs/2509.25839 https://

RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
While high-dimensional embedding vectors are being increasingly employed in various tasks like Retrieval-Augmented Generation and Recommendation Systems, popular dimensionality reduction (DR) methods such as PCA and UMAP have rarely been adopted for accelerating the retrieval process due to their inability of preserving the nearest neighbor (NN) relationship among vectors. Empowered by neural networks' optimization capability and the bounding effect of Rayleigh quotient, we propose a Regularize…

Equivariant Geometric Scattering Networks via Vector Diffusion Wavelets
David R. Johnson, Rishabh Anand, Smita Krishnaswamy, Michael Perlmutter
https://arxiv.org/abs/2510.01022 …

Equivariant Geometric Scattering Networks via Vector Diffusion Wavelets
We introduce a novel version of the geometric scattering transform for geometric graphs containing scalar and vector node features. This new scattering transform has desirable symmetries with respect to rigid-body roto-translations (i.e., $SE(3)$-equivariance) and may be incorporated into a geometric GNN framework. We empirically show that our equivariant scattering-based GNN achieves comparable performance to other equivariant message-passing-based GNNs at a fraction of the parameter count.