arXiv:2601.05427v1 Announce Type: new Abstract: In many multi-agent systems, agents interact repeatedly and are expected to settle into equilibrium behavior over time. Yet in practice, behavior often drifts, and detecting such deviations in real time remains an open challenge. We introduce a sequential testing framework that monitors whether observed play in repeated games is consistent with equilibrium, without assuming a fixed sample size. Our approach builds on the e-value framework for safe anytime-valid inference: by “betting” against equilibrium, […]

Ver mais

I’ve been watching how companies procure AI infrastructure lately, and it’s honestly a bit of a train wreck. Most procurement teams and CFOs are making decisions based on one single metric: $/GPU/hour. The problem? The sticker price on a cloud pricing sheet is almost never the real cost. I’m considering offering a specialized TCO (Total Cost of Ownership) Consulting Service for AI compute, and I want to see if there’s a real market for it. Based on my […]

Ver mais

Hi everyone, I’m Jacob, the creator of the NotebookLM-MCP that I shared here a while back. Today I’m excited to reveal my next project: NotebookLM-CLI 🚀 What is it? A full-featured command-line interface for NotebookLM. Same HTTP/RPC approach as the MCP (no browser automation, except for login process and cookie/tokens extraction), but packaged as a standalone CLI you can run directly from your terminal. Installation and example commands: # Using pip pip install notebooklm-cli # Using pipx (recommended […]

Ver mais

arXiv:2601.16282v1 Announce Type: new Abstract: Contemporary automated scientific discovery has focused on agents for generating scientific experiments, while systems that perform higher-level scientific activities such as theory building remain underexplored. In this work, we formulate the problem of synthesizing theories consisting of qualitative and quantitative laws from large corpora of scientific literature. We study theory generation at scale, using 13.7k source papers to synthesize 2.9k theories, examining how generation using literature-grounding versus parametric knowledge, and accuracy-focused versus novelty-focused […]

Ver mais

arXiv:2510.23463v3 Announce Type: replace-cross Abstract: Federated Learning (FL) is a distributed learning paradigm that preserves privacy by eliminating the need to exchange raw data during training. In its prototypical edge instantiation with underlying wireless transmissions enabled by analog over-the-air computing (AirComp), referred to as emph{over-the-air FL (AirFL)}, the inherent channel noise plays a unique role of emph{frenemy} in the sense that it degrades training due to noisy global aggregation while providing a natural source of randomness for privacy-preserving […]

Ver mais

arXiv:2601.14289v1 Announce Type: new Abstract: Understanding research papers remains challenging for foundation models due to specialized scientific discourse and complex figures and tables, yet existing benchmarks offer limited fine-grained evaluation at scale. To address this gap, we introduce RPC-Bench, a large-scale question-answering benchmark built from review-rebuttal exchanges of high-quality computer science papers, containing 15K human-verified QA pairs. We design a fine-grained taxonomy aligned with the scientific research flow to assess models’ ability to understand and answer why, what, […]

Ver mais

The previous post talked about doing perfect shuffles: divide a deck in half, and alternately let one card from each half fall. It matters which half lets a card fall first. If the top half’s bottom card falls first, this is called an in-shuffle. If the bottom half’s bottom card falls first, it’s called an out-shuffle. With an out-shuffle, the top and bottom cards don’t move. Presumably it’s called an out-shuffle because the outside cards remain in place. […]

Ver mais

The growing demand for cost-efficient digital transactions has driven the need for scalable and low-cost payment solutions. Traditional blockchain-based transactions suffer from high fees and slow processing times, making decentralized off-chain payment networks a promising alternative. In this paper, we propose SpeedyMurmurs, an AI-enhanced decentralized routing algorithm that significantly reduces payment processing costs and transaction delays. Our approach optimizes payment routing efficiency through embedding-based path discovery, reducing routing overhead by up to two orders of magnitude and cutting […]

Ver mais

arXiv:2601.15459v1 Announce Type: new Abstract: This study presents an integrated framework for enhancing the safety and operational efficiency of robotic arms in laparoscopic surgery by addressing key challenges in collision detection and minimum distance estimation. By combining analytical modeling, real-time simulation, and machine learning, the framework offers a robust solution for ensuring safe robotic operations. An analytical model was developed to estimate the minimum distances between robotic arms based on their joint configurations, offering precise theoretical calculations that […]

Ver mais