technocracy

Contrastive Forward-Forward (CFF) learning trains Vision Transformers layer by layer against supervised contrastive objectives. CFF training can be sensitive to random seed, but the sources of this instability are poorly understood. We focus on one implementation detail: the positive-pair margin in the contrastive loss is applied through saturating similarity clamping, $min(s + m,, 1)$. We prove that an alternative formulation, subtracting the margin after the log-probability, is gradient-neutral under the mean-over-positives reduction. On CIFAR-10 ($2 times 2$ factorial, […]

Ver mais

arXiv:2601.14460v1 Announce Type: new Abstract: The integration of generative AI into information access systems often presents users with synthesized answers that lack transparency. This study investigates how different types of explanations can influence user trust in responses from retrieval-augmented generation systems. We conducted a controlled, two-stage user study where participants chose the more trustworthy response from a pair-one objectively higher quality than the other-both with and without one of three explanation types: (1) source attribution, (2) factual grounding, […]

Ver mais

Internet of underwater things (IoUT) is increasingly gathering attention with the aim of monitoring sea life and deep ocean environment, underwater surveillance as well as maintenance of underwater installments. However, conventional IoUT devices, reliant on battery power, face limitations in lifespan and pose environmental hazards upon disposal. This paper introduces a sustainable approach for simultaneous information uplink from the IoUT devices and acoustic energy transfer (AET) to the devices via an autonomous underwater vehicle (AUV), potentially enabling them […]

Ver mais

arXiv:2604.16964v1 Announce Type: new Abstract: Floating-point square-root computation is a power- and delay-critical operation in edge-AI, signal-processing, and embedded systems. Conventional implementations typically rely on multipliers or iterative pipelines, resulting in increased hardware complexity, switching activity, and energy consumption. This work presents E2AFS, a lightweight and fully multiplier-free floating-point square-root architecture optimized for energy-efficient computation. By reducing logic depth and minimizing switching activity, the proposed design achieves substantial improvements in hardware efficiency and performance. FPGA implementation on an […]

Ver mais

Introduction: From IDEs to Agentic Command Centers :::info We have officially crossed the event horizon. ::: For decades, the Integrated Development Environment (IDE) was a passive canvas—a glorified typewriter that waited for your keystrokes. :::warning As of February 2026, with the maturity of Google Antigravity, the IDE is dead. ::: We have entered the era of the Agentic Command Center. Antigravity is not a “coding assistant.” :::tip To treat it as such is to buy a Ferrari and push […]

Ver mais

While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they discard past rollouts. Existing experience replay methods address this by reusing accurate samples for direct policy updates, but this often incurs high computational costs and causes mode collapse via overfitting. We argue that historical data should prioritize sustaining diversity rather than simply reinforcing accuracy. To this end, we propose Dynamic Jensen-Shannon Replay (DyJR), a simple yet effective regularization framework using a […]

Ver mais

arXiv:2601.12230v1 Announce Type: new Abstract: We study classical-quantum (C-Q) channel resolvability. C-Q channel resolvability has been proved by only random coding in the literature. In our previous study, we proved channel resolvability by deterministic coding, using multiplicative weight update algorithm. We extend this approach to C-Q channels and prove C-Q channel resolvability by deterministic coding, using the matrix multiplicative weight update algorithm. This is the first approach to C-Q channel resolvability using deterministic coding.

Ver mais

arXiv:2510.07088v4 Announce Type: replace Abstract: Fourier analysis on the Boolean hypercube is fundamentally defined as the orthogonal decomposition of the space of pseudo-Boolean functions with respect to the uniform probability measure. In this work, we propose an ANOVA-based generalization of the Fourier decomposition on the Boolean hypercube endowed with any arbitrary probability measure. We provide an emph{explicit} decomposition basis which generalizes the Walsh-Hadamard (or parity functions) basis under any emph{arbitrary} probability measure on the Boolean hypercube. We formulate […]

Ver mais