technocracy

arXiv:2601.07956v1 Announce Type: new Abstract: This paper presents a method for estimating parameters that form a general model for human pilot response for specific tasks. The human model is essential for the dynamic analysis of piloted vehicles. Data are generated on a simulator with multiple trials being incorporated to find the single model that best describes the data. The model is found entirely in the time domain by constructing a constrained optimization problem. This optimization problem implicitly represents […]

Ver mais

arXiv:2603.26349v1 Announce Type: new Abstract: Accurate uncertainty quantification is crucial for making reliable decisions in various supervised learning scenarios, particularly when dealing with complex, multimodal data such as images and text. Current approaches often face notable limitations, including rigid assumptions and limited generalizability, constraining their effectiveness across diverse supervised learning tasks. To overcome these limitations, we introduce Generative Score Inference (GSI), a flexible inference framework capable of constructing statistically valid and informative prediction and confidence sets across a […]

Ver mais

arXiv:2603.17092v1 Announce Type: new Abstract: Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tuning these policies directly on hardware is problematic, as it poses risks of mechanical failure and suffers from high sample inefficiency. In this paper, we address the challenge of safely and efficiently fine-tuning reinforcement learning (RL) policies for dynamic locomotion tasks. Specifically, we focus on fine-tuning policies learned in simulation directly on hardware, while explicitly enforcing […]

Ver mais

arXiv:2603.03291v1 Announce Type: new Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By systematically measuring biases in five high-quality RMs, including the state-of-the-art, we find that issues persist despite prior work with respect to length, sycophancy, and overconfidence. We also discover new issues related to bias toward model-specific styles and answer-order. We categorize […]

Ver mais

One-shot federated learning (OSFL) reduces the communication cost and privacy risks of iterative federated learning by constructing a global model with a single round of communication. However, most existing methods struggle to achieve robust performance on real-world domains such as medical imaging, or are inefficient when handling non-IID (Independent and Identically Distributed) data. To address these limitations, we introduce FALCON, a framework that enhances the effectiveness of OSFL over non-IID image data. The core idea of FALCON is […]

Ver mais

How are you, hacker? 🪐Want to know what’s trending right now?: The Techbeat by HackerNoon has got you covered with fresh content from our trending stories of the day! Set email preference here. ## SERP Benchmarks: Success Rates and Latency at Scale By @brightdata [ 8 Min read ] ​​We benchmark SERP APIs for success rate, ​​speed, and stability under load. Learn which setup delivers consistent results for AI agents ​​and deep research. Read More. SecurityMetrics Announces Suite […]

Ver mais

Published on January 25, 2026 6:33 PM GMT This post was originally published on November 11th, 2025. I’ve been spending some time reworking and cleaning up the Inkhaven posts I’m most proud of, and completed the process for this one today.   Today, Canada officially lost its measles elimination status. Measles was previously declared eliminated in Canada in 1998, but countries lose that status after 12 months of continuous transmission. Here are some articles about the the fact […]

Ver mais

Identifying physical laws from noisy observational data is a central challenge in scientific machine learning. We present Minimum-Action Learning (MAL), a framework that selects symbolic force laws from a pre-specified basis library by minimizing a Triple-Action functional combining trajectory reconstruction, architectural sparsity, and energy-conservation enforcement. A wide-stencil acceleration-matching technique reduces noise variance by 10,000x, transforming an intractable problem (SNR ~0.02) into a learnable one (SNR ~1.6); this preprocessing is the critical enabler shared by all methods tested, including […]

Ver mais

arXiv:2602.08185v1 Announce Type: new Abstract: Discriminative Random Walks (DRWs) are a simple yet powerful tool for semi-supervised node classification, but their theoretical foundations remain fragmentary. We revisit DRWs through the lens of information geometry, treating the family of class-specific hitting-time laws on an absorbing Markov chain as a statistical manifold. Starting from a log-linear edge-weight model, we derive closed-form expressions for the hitting-time probability mass function, its full moment hierarchy, and the observed Fisher information. The Fisher matrix […]

Ver mais