technocracy

arXiv:2603.23633v1 Announce Type: new Abstract: Large language models can generate runnable software artifacts, but their security remains difficult to evaluate end to end. This study examines that problem through a Detect–Repair–Verify (DRV) workflow, in which vulnerabilities are detected, repaired, and then rechecked with security and functional tests. It addresses four gaps in current evidence: the lack of test-grounded benchmarks for LLM-generated artifacts, limited evidence on pipeline-level effectiveness, unclear reliability of detection reports as repair guidance, and uncertain repair […]

Ver mais

arXiv:2602.22394v1 Announce Type: new Abstract: Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream tasks. Through systematic analysis of artifacts in ViTs, we find that their fundamental mechanisms have yet to be sufficiently elucidated. In this paper, through systematic analysis, we conclude that these artifacts originate from a lazy aggregation behavior: ViT uses semantically irrelevant background patches as shortcuts […]

Ver mais

arXiv:2603.03412v1 Announce Type: new Abstract: Recent advances in generative image editing have enabled transformative applications, from professional head shot generation to avatar stylization. However, these systems often require uploading high-fidelity facial images to third-party models, raising concerns around biometric privacy, data misuse, and user consent. We propose a privacy-preserving pipeline that supports high-quality editing while keeping users in control over their biometric data in face-centric use cases. Our approach separates identity-sensitive regions from editable image context using on-device […]

Ver mais

arXiv:2604.17007v1 Announce Type: new Abstract: Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present MobileAgeNet, a lightweight age-regression framework that achieves an MAE of 4.65 years on the UTKFace held-out test set while maintaining efficient on-device inference with an average latency of 14.4 ms measured using the AI Benchmark application. The model is built on a pretrained MobileNetV3-Large backbone combined with a compact regression […]

Ver mais

arXiv:2604.09681v1 Announce Type: new Abstract: With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time inference. However, existing approaches often fail to dynamically adapt to heterogeneous video content and fluctuating resource conditions, resulting in suboptimal routing efficiency and high computational costs. In this paper, we propose R2E-VID, a two-stage robust routing framework via temporal gating for elastic edge-cloud video inference. In the first stage, R2E-VID introduces a temporal gating […]

Ver mais

TLDR; We were overpaying for OCR, so we compared flagship models with cheaper and older models. New mini-bench + leaderboard. Free tool to test your own documents. Open Source. We’ve been looking at OCR / document extraction workflows and kept seeing the same pattern: Too many teams are either stuck in legacy OCR pipelines, or are overpaying badly for LLM calls by defaulting to the newest/ biggest model. We put together a curated set of 42 standard documents […]

Ver mais

arXiv:2603.20325v1 Announce Type: new Abstract: Deep learning models have achieved strong performance in medical image analysis, but their internal decision processes remain difficult to interpret. Concept Bottleneck Models (CBMs) partially address this limitation by structuring predictions through human-interpretable clinical concepts. However, existing CBMs typically overlook the contextual dependencies among concepts. To address these issues, we propose an end-to-end interpretable framework emph{DCG-Net} that integrates multimodal alignment with structured concept reasoning. DCG-Net introduces a Dual Cross-Attention module that replaces cosine […]

Ver mais

arXiv:2603.26709v1 Announce Type: new Abstract: Autonomous platforms require accurate positioning to complete their tasks. To this end, a Kalman filter-based algorithms, such as the extended Kalman filter or invariant Kalman filter, utilizing inertial and external sensor fusion are applied. To cope with real-world scenarios, adaptive noise estimation methods have been developed primarily for classical Euclidean formulations. However, these methods remain largely unexplored in the tangent Lie space, despite it provides a principled geometric framework with favorable error dynamics […]

Ver mais

arXiv:2602.23116v2 Announce Type: replace-cross Abstract: We consider the problem of contextual online RLHF with general preferences, where the goal is to identify the Nash Equilibrium. We adopt the Generalized Bilinear Preference Model (GBPM) to capture potentially intransitive preferences via low-rank, skew-symmetric matrices. We investigate general preference learning with any strongly convex regularizer and regularization strength $eta^{-1}$, generalizing beyond prior work limited to reverse KL-regularization. Central to our analysis is proving that the dual gap of the greedy policy […]

Ver mais

We present a finite-range experimental note on an additive structure induced by twin- prime starts in Goldbach space. Let a twin-prime start be an integer a such that both a and a + 2 are prime, and define the start-sum set S = {a + c : a, c are twin-prime starts}. From each such sum we associate the three-term block {s, s + 2, s + 4}, and we study the even integers covered by the union […]

Ver mais