Tootfinder

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
Shashanka Venkataramanan, Valentinos Pariza, Mohammadreza Salehi, Lukas Knobel, Spyros Gidaris, Elias Ramzi, Andrei Bursuc, Yuki M. Asano
https://arxiv.org/abs/2507.14137

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many cases surpasses the performance of state-of-the-art proprietary models, e.g., DINOv2, CLIP, SigLIPv2, etc. Our approach is grounded in a transparent training pipeline inspired by Web-SSL and uses publicly available data: ImageNet-21K and a subset of ReLAION-2B. Beyond model release, we tackle critical limitations in SSL clustering methods. While mo…

Scalable Chrysopoeia via $(n, 2n)$ Reactions Driven by Deuterium-Tritium Fusion Neutrons
Adam Rutkowski, Jake Harter, Jason Parisi
https://arxiv.org/abs/2507.13461

Scalable Chrysopoeia via $(n, 2n)$ Reactions Driven by Deuterium-Tritium Fusion Neutrons
A scalable approach for chrysopoeia -- the transmutation of base metals into gold -- has been pursued for millennia. While there have been small-scale demonstrations in particle accelerators and proposals involving thermal neutron capture, no economically attractive approach has yet been identified. We show a new scalable method to synthesize stable gold (\ce{^{197}Au}) from the abundant mercury isotope $\mathrm{^{198}Hg}$ using $(n, 2n)$ reactions in a specialized neutron multiplier layer of a…

FuSeFL: Fully Secure and Scalable Cross-Silo Federated Learning
Sahar Ghoflsaz Ghinani, Elaheh Sadredini
https://arxiv.org/abs/2507.13591 https://

FuSeFL: Fully Secure and Scalable Cross-Silo Federated Learning
Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains. While existing approaches employ cryptographic techniques such as homomorphic encryption, differential privacy, or secure multiparty computation to mitigate inference attacks-including model inversion, membership inference, and gradient leakage-they often suffer from high computational, communication, or memory overheads. Moreover, many methods overl…

Efficient and Scalable Self-Healing Databases Using Meta-Learning and Dependency-Driven Recovery
Joydeep Chandra, Prabal Manhas
https://arxiv.org/abs/2507.13757

Efficient and Scalable Self-Healing Databases Using Meta-Learning and Dependency-Driven Recovery
This study explored the development of a novel self-healing framework for databases using meta-learning and reinforcement learning techniques. The primary objective was to address the challenges of real-time adaptability and minimal retraining in dynamic workload environments. The proposed approach integrated Model-Agnostic Meta-Learning (MAML) with reinforcement learning to enable anomaly detection and corrective actions that adapted swiftly to evolving database conditions. Multi-objective opt…

Tomorrow, and tomorrow, and tomorrow
Creeps in this petty pace from day to day,
To the last syllable of recorded time
...It is a tale
Told by an idiot, full of sound and fury,
Signifying nothing.
#Macbeth

Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiatio
Yaowen Hu, Wenxuan Tu, Yue Liu, Xinhang Wan, Junyi Yan, Taichun Zhou, Xinwang Liu
https://arxiv.org/abs/2507.13368

Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiatio
Deep graph clustering (DGC), which aims to unsupervisedly separate the nodes in an attribute graph into different clusters, has seen substantial potential in various industrial scenarios like community detection and recommendation. However, the real-world attribute graphs, e.g., social networks interactions, are usually large-scale and attribute-missing. To solve these two problems, we propose a novel DGC method termed \underline{\textbf{C}}omplementary \underline{\textbf{M}}ulti-\underline{\te…

Maximizing solubility in rock salt high-entropy oxides
Matthew Furst, Joseph Petruska, Dhiya Srikanth, Jacob T. Sivak, Susan B. Sinnott, Christina M. Rost, Jon-Paul Maria, Saeed S. I. Almishal
https://arxiv.org/abs/2506.15604

Maximizing solubility in rock salt high-entropy oxides
To explore and quantitatively map the cation-size mismatch solubility limits in high-entropy oxides (HEOs), we report on Ca$^{2+}$ substitution in prototypical MgCoNiCuZnO, because, while isovalent, Ca$^{2+}$ is 38% larger than its partners' average ionic radii. Using the thermodynamics-grounded bond-length distribution descriptor, we identify Ca$^{2+}$-Cu$^{2+}$ interactions as the primary prospective lattice destabilizer. Bulk synthesis confirms only 4% Ca solubility with Cu at 950$^o$C, mode…

Scalable dissipative quantum error correction for discrete-variable codes
Ivan Rojkov, Elias Zapusek, Florentin Reiter
https://arxiv.org/abs/2507.12534 htt…

Scalable dissipative quantum error correction for discrete-variable codes
Dissipative quantum error correction (QEC) autonomously protects quantum information using engineered dissipation and offers a promising alternative to error correction via measurement and feedback. However, scalability remains a challenge, as correcting high-weight errors typically requires increasing dissipation rates and exponentially many correction operators. Here, we present a scalable dissipative QEC protocol for discrete-variable codes, correcting multi-qubit errors via a trickle-down m…

🇺🇦 #NowPlaying on KEXP's #DriveTime
Erykah Badu:
🎵 Bag Lady
#ErykahBadu
https://traadsaru.bandcamp.com/track/erykah-badu-bag-lady-traadsaru-soulful-house-remix
https://open.spotify.com/track/7BgUcOjSOlKJXASLgJ6bx1

Toward a Lightweight, Scalable, and Parallel Secure Encryption Engine
Rasha Karakchi, Rye Stahle-Smith, Nishant Chinnasami, Tiffany Yu
https://arxiv.org/abs/2506.15070

Toward a Lightweight, Scalable, and Parallel Secure Encryption Engine
The exponential growth of Internet of Things (IoT) applications has intensified the demand for efficient, high-throughput, and energy-efficient data processing at the edge. Conventional CPU-centric encryption methods suffer from performance bottlenecks and excessive data movement, especially in latency-sensitive and resource-constrained environments. In this paper, we present SPiME, a lightweight, scalable, and FPGA-compatible Secure Processor-in-Memory Encryption architecture that integrates t…