Tootfinder

RepuNet: A Reputation System for Mitigating Malicious Clients in DFL
Isaac Marroqui Penalva, Enrique Tom\'as Mart\'inez Beltr\'an, Manuel Gil P\'erez, Alberto Huertas Celdr\'an
https://arxiv.org/abs/2506.19892

RepuNet: A Reputation System for Mitigating Malicious Clients in DFL
Decentralized Federated Learning (DFL) enables nodes to collaboratively train models without a central server, introducing new vulnerabilities since each node independently selects peers for model aggregation. Malicious nodes may exploit this autonomy by sending corrupted models (model poisoning), delaying model submissions (delay attack), or flooding the network with excessive messages, negatively affecting system performance. Existing solutions often depend on rigid configurations or addition…

My article just out:
Progressive Jews (and non-Jews too!) need to revive the social democratic politics of solidarity. It brings poor & middle together, in contrast to the politics of far-left "allyship" & elite charity which both drive them apart.
https://www.

After Zohran Mamdani’s upset, there’s a way forward for pro-Israel progressives
In the fight for economic fairness for all, Jews shouldn't have to give up on defending their particular interests, writes a long-time contributor to Dissent magazine.

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
Xiaoxu Zhu, Junhua Li
https://arxiv.org/abs/2507.17851 https://arxiv.org/pdf/…

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
Speech pretrained models contain task-specific information across different layers, but decoupling content and timbre information remains challenging as removing speaker-specific information often causes content loss. Current research lacks direct metrics to quantify timbre residual in model encodings, relying on indirect evaluation through downstream tasks. This paper addresses these challenges through interpretability-based speaker disentanglement in speech pretraining models. We quantitative…

Decentralized Federated Learning of Probabilistic Generative Classifiers
Aritz P\'erez, Carlos Echegoyen, Guzm\'an Santaf\'e
https://arxiv.org/abs/2507.17285

Decentralized Federated Learning of Probabilistic Generative Classifiers
Federated learning is a paradigm of increasing relevance in real world applications, aimed at building a global model across a network of heterogeneous users without requiring the sharing of private data. We focus on model learning over decentralized architectures, where users collaborate directly to update the global model without relying on a central server. In this context, the current paper proposes a novel approach to collaboratively learn probabilistic generative classifiers with a parame…

Institutional Noise, Strategic Deviation, and Intertemporal Collapse: A Formal Model of Miner Behaviour under Protocol Uncertainty
Craig Steven Wright
https://arxiv.org/abs/2506.20992

Institutional Noise, Strategic Deviation, and Intertemporal Collapse: A Formal Model of Miner Behaviour under Protocol Uncertainty
This paper develops a formal game-theoretic model to examine how protocol mutability disrupts cooperative mining behaviour in blockchain systems. Using a repeated game framework with stochastic rule shocks, we show that even minor uncertainty in institutional rules increases time preference and induces strategic deviation. Fixed-rule environments support long-term investment and stable equilibrium strategies; in contrast, mutable protocols lead to short-termism, higher discounting, and collapse…

This https://arxiv.org/abs/2412.03554 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Categorize and randomize: a permissive model of stochastic choice
We model stochastic choices with categorization. The agent preliminarly groups alternatives in homogenous disjoint classes, then randomly chooses one class and randomly picks an item within the selected class. We give a formal definition of a choice generated by this procedure, and provide an axiomatic characterization. The characterizing properties allow an external analyst to elicit that categorization is applied. In a broader interpretation, the model allows to describe the observed choice a…

Mastodon updates its terms to prohibit AI model training starting July 1, and enforces a new age limit of 16 for users globally (Ivan Mehta/TechCrunch)
https://techcrunch.com/2025/06/17/mastodon-updates-its-terms-to-prohibit-ai-model-tra…

Mastodon updates its terms to prohibit AI model training | TechCrunch
Days after Elon Musk-owned X updated its terms to explicitly prohibit AI model training, decentralized social network Mastodon updated its own rules to bar any kind of model training, as well.

https://techcrunch.com/2025/06/17/mastodon-updates-its-terms-to-prohibit-ai-model-training/
Mastodon updates its terms to prohibit AI model training

Mastodon updates its terms to prohibit AI model training | TechCrunch
Days after Elon Musk-owned X updated its terms to explicitly prohibit AI model training, decentralized social network Mastodon updated its own rules to bar any kind of model training, as well.

Mastodon updates its terms to prohibit AI model training
https://techcrunch.com/2025/06/17/mastodon-updates-its-terms-to-prohibit-ai-model-training/

Mastodon updates its terms to prohibit AI model training | TechCrunch
Days after Elon Musk-owned X updated its terms to explicitly prohibit AI model training, decentralized social network Mastodon updated its own rules to bar any kind of model training, as well.

DECA: A Near-Core LLM Decompression Accelerator Supporting Out-of-Order Invocation
Gerasimos Gerogiannis (Intel Corporation,University of Illinois at Urbana-Champaign), Stijn Eyerman (Intel Corporation), Evangelos Georganas (Intel Labs), Wim Heirman (Intel Corporation), Josep Torrellas (University of Illinois at Urbana-Champaign)
https://

DECA: A Near-Core LLM Decompression Accelerator Supporting Out-of-Order Invocation
To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core generalized matrix multiplication (GeMM) hardware engines, they need to be dequantized and de-sparsified. This is currently performed in software with vector operations. Unfortunately, this approach delivers only modest performance. Moreover, it is hard to unders…