technocracy

Efficient estimation of causal and structural parameters can be automated using the Riesz representation theorem and debiased machine learning (DML). We present genriesz, an open-source Python package that implements automatic DML and generalized Riesz regression, a unified framework for estimating Riesz representers by minimizing empirical Bregman divergences. This framework includes covariate balancing, nearest-neighbor matching, calibrated estimation, and density ratio estimation as special cases. A key design principle of the package is automatic regressor balancing (ARB): given a Bregman […]

Ver mais

I’ve been building RL training environments for the upcoming ARC-AGI-3 competition — 13 games, 1,872 levels — and wanted to share them with the community. The environments are inspired by The Witness) — each game teaches a different abstract rule (path constraints, region partitioning, symmetry, etc.) through progressive difficulty with zero instructions. RL-specific details: – OpenEnv compatible (Gymnasium-style API) – 3 reward modes: sparse (task completion only), shaped (step-level heuristics), arc_score (official ARC metric) – Teaching mode: annotate […]

Ver mais

arXiv:2604.18610v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for […]

Ver mais

arXiv:2601.07973v1 Announce Type: new Abstract: Generative AI models ought to be useful and safe across cross-cultural contexts. One critical step toward this goal is understanding how AI models adhere to sociocultural norms. While this challenge has gained attention in NLP, existing work lacks both nuance and coverage in understanding and evaluating models’ norm adherence. We address these gaps by introducing a taxonomy of norms that clarifies their contexts (e.g., distinguishing between human-human norms that models should recognize and […]

Ver mais

arXiv:2602.10259v1 Announce Type: new Abstract: This study introduces a new object detection dataset of pedestrians using mobility aids, named PMMA. The dataset was collected in an outdoor environment, where volunteers used wheelchairs, canes, and walkers, resulting in nine categories of pedestrians: pedestrians, cane users, two types of walker users, whether walking or resting, five types of wheelchair users, including wheelchair users, people pushing empty wheelchairs, and three types of users pushing occupied wheelchairs, including the entire pushing group, […]

Ver mais

At Serokell, we have been working hard for some time now to help add dependent types to Haskell. It is the primary goal of our dedicated GHC team, currently consisting of Vladislav Zavialov and Andrei Borzenkov. We have occasionally shared our progress on Discourse in the past, though in an irregular manner, which has left some wondering if we are still actively working on it. Yes, we are! However, retrofitting ergonomic dependent types is a very complex task. […]

Ver mais

arXiv:2506.10586v2 Announce Type: replace-cross Abstract: Determining whether an algorithmic decision-making system discriminates against a specific demographic typically involves comparing a single point estimate of a fairness metric against a predefined threshold. This practice is statistically brittle: it ignores sampling error and treats small demographic subgroups the same as large ones. The problem intensifies in intersectional analyses, where multiple sensitive attributes are considered jointly, giving rise to a larger number of smaller groups. As these groups become more granular, […]

Ver mais

Teilhard depicts humanity as the Earth awakening to itself as evolution rises toward ever-greater unity. Love and consciousness converge into a planetary spirit, but this ascent, he insists, cannot endure without religion—our innate need for an absolute that calls us forward. In the universe’s unfolding, God emerges as evolution’s necessary summit and sustaining fire.

Ver mais

Web3 has a branding problem. For years, it trained people to associate it with noise. Big promises. Bigger token launches. Endless “future of the internet” speeches. Communities that looked active until the price fell. Products that demanded tutorials before they delivered value. Too much of Web3 felt like an industry asking users to care about its architecture more than its usefulness. That was never going to scale. Because outside crypto circles, normal users do not care what a […]

Ver mais