technocracy

arXiv:2601.05432v1 Announce Type: new Abstract: The image geolocalization task aims to predict the location where an image was taken anywhere on Earth using visual clues. Existing large vision-language model (LVLM) approaches leverage world knowledge, chain-of-thought reasoning, and agentic capabilities, but overlook a common strategy used by humans — using maps. In this work, we first equip the model textit{Thinking with Map} ability and formulate it as an agent-in-the-map loop. We develop a two-stage optimization scheme for it, including […]

Ver mais

arXiv:2603.23629v1 Announce Type: new Abstract: Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at inference time. Using a difference-in-means method, we estimate layer-wise steering vectors for five language/library pairs and add them to model hidden states during generation. Across three open-weight code LLMs, these interventions substantially increase generation toward the target ecosystem under neutral prompts […]

Ver mais

Modern financial institutions process millions of trades every day, and the underlying infrastructure that supports this volume must be fast, fault-tolerant, and accurate down to the microsecond. Over the past several years, event-driven architecture has emerged as the dominant pattern for building these systems, and Apache Kafka has become the backbone of many mission-critical trade processing pipelines. This post walks through the core architectural decisions, technical patterns, and operational lessons I have gathered working on high-throughput trade systems […]

Ver mais

arXiv:2603.25923v1 Announce Type: new Abstract: Deep learning models have shown promise in EEG-based outcome prediction for comatose patients after cardiac arrest, but their reliability is often compromised by subtle forms of data leakage. In particular, when long EEG recordings are segmented into short windows and reused across multiple training stages, models may implicitly encode and propagate label information, leading to overly optimistic validation performance and poor generalization. In this study, we identify a previously overlooked form of data […]

Ver mais

The quality of data augmentation serves as a critical determinant for the performance of contrastive learning in EEG tasks. Although this paradigm is promising for utilizing unlabeled data, static or random augmentation strategies often fail to preserve intrinsic information due to the non-stationarity of EEG signals where statistical properties change over time. To address this, we propose RL-BioAug, a framework that leverages a label-efficient reinforcement learning (RL) agent to autonomously determine optimal augmentation policies. While utilizing only a […]

Ver mais

Agentic Engineering Patterns > The defining characteristic of a coding agent is that it can execute the code that it writes. This is what makes coding agents so much more useful than LLMs that simply spit out code without any way to verify it. Never assume that code generated by an LLM works until that code has been executed. Coding agents have the ability to confirm that the code they have produced works as intended, or iterate further […]

Ver mais

Why 2026 feels different In 2026, low code and no code are not side tools anymore. They are becoming a default path to ship internal workflows (Gartner’s low code forecast), portals, dashboards, and even customer experiences, because the pressure to deliver faster never went away. I see many teams adopt a platform quickly, build a few apps, and then run into the same problems: messy ownership, risky data access, inconsistent quality, and a painful scaling story. This guide […]

Ver mais

arXiv:2601.03410v1 Announce Type: new Abstract: Molecular subtyping of PDAC into basal-like and classical has established prognostic and predictive value. However, its use in clinical practice is limited by cost, turnaround time, and tissue requirements, thereby restricting its application in the management of PDAC. We introduce PanSubNet, an interpretable deep learning framework that predicts therapy-relevant molecular subtypes directly from standard H&E-stained WSIs. PanSubNet was developed using data from 1,055 patients across two multi-institutional cohorts (PANCAN, n=846; TCGA, n=209) with […]

Ver mais

arXiv:2602.05033v1 Announce Type: new Abstract: Learning meaningful causal representations from observations has emerged as a crucial task for facilitating machine learning applications and driving scientific discoveries in fields such as climate science, biology, and physics. This process involves disentangling high-level latent variables and their causal relationships from low-level observations. Previous work in this area that achieves identifiability typically focuses on cases where the observations are either i.i.d. or follow a latent discrete-time process. Nevertheless, many real-world settings require […]

Ver mais