technocracy

arXiv:2601.20083v1 Announce Type: new Abstract: We present LLaTTE (LLM-Style Latent Transformers for Temporal Events), a scalable transformer architecture for production ads recommendation. Through systematic experiments, we demonstrate that sequence modeling in recommendation systems follows predictable power-law scaling similar to LLMs. Crucially, we find that semantic features bend the scaling curve: they are a prerequisite for scaling, enabling the model to effectively utilize the capacity of deeper and longer architectures. To realize the benefits of continued scaling under strict […]

Ver mais

In late 2025, the Reuters Institute for the Study of Journalism reported that [global publishers have already lost ]()**33% of search referral traffic year over year with media leaders projecting an additional *40%+ decline* as AI-generated answers replace traditional discovery paths. That data point matters far beyond journalism. It confirms something B2B marketers are now feeling in real time: buyers are no longer navigating the web, they are prompting AI systems to do the thinking for them. Call […]

Ver mais

The core of molecular dynamics simulation fundamentally lies in the interatomic potential. Traditional empirical potentials lack accuracy, while first-principles methods are computationally prohibitive. Machine learning interatomic potentials (MLIPs) promise near-quantum accuracy at linear cost, but existing models still face challenges in efficiency and stability. We presents Machine Learning Advances Neural Network (MLANet), an efficient and robust graph neural network framework. MLANet introduces a dual-path dynamic attention mechanism for geometry-aware message passing and a multi-perspective pooling strategy to construct […]

Ver mais

Transformer-based diffusion models have demonstrated remarkable performance at generating high-quality samples. However, our theoretical understanding of the reasons for this success remains limited. For instance, existing models are typically trained by minimizing a denoising objective, which is equivalent to fitting the score function of the training data. However, we do not know why transformer-based models can match the score function for denoising, or why gradient-based methods converge to the optimal denoising model despite the non-convex loss landscape. To […]

Ver mais

Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as effective self-correction behaviors emerge only rarely, making learning signals extremely sparse. To address this challenge, we propose correction-specific rollouts (Octopus), an RL rollout augmentation framework that synthesizes dense self-correction examples by recombining existing rollouts. This augmentation simultaneously improves sample efficiency due to rollout reuse and stabilizes RL optimization through balanced supervision. Furthermore, we introduce a […]

Ver mais

arXiv:2604.01404v1 Announce Type: new Abstract: Language models can answer many entity-centric factual questions, but it remains unclear which internal mechanisms are involved in this process. We study this question across multiple language models. We localize entity-selective MLP neurons using templated prompts about each entity, and then validate them with causal interventions on PopQA-based QA examples. On a curated set of 200 entities drawn from PopQA, localized neurons concentrate in early layers. Negative ablation produces entity-specific amnesia, while controlled […]

Ver mais

Legal Intern Alexandra Rhodes contributed to this blog post.  EFF filed an amicus brief urging the Arizona District Court to protect public school students’ freedom of speech and privacy by holding that the use of a school-issued laptop or email account does not categorically mean a student is “on campus.” We argued that students need private digital spaces beyond their school’s reach to speak freely, without the specter of constant school surveillance and punishment.   Surveillance Software Exposed a […]

Ver mais