arXiv:2601.14277v1 Announce Type: new Abstract: Quantization is a practical technique for making large language models easier to deploy by reducing the precision used to store and operate on model weights. This can lower memory use and improve runtime feasibility on constrained hardware, which is especially relevant for users running models locally. Quantization in llama.cpp enables large language models to run on commodity hardware, but available formats are often evaluated inconsistently, making it hard to choose among schemes. We […]

Ver mais

Lagrangian Neural Networks (LNNs) can learn arbitrary Lagrangians from trajectory data, but their unusual optimization objective leads to significant training instabilities that limit their application to complex systems. We propose several improvements that address these fundamental challenges, namely, a Hessian regularization scheme that penalizes unphysical signatures in the Lagrangian’s second derivatives with respect to velocities, preventing the network from learning unstable dynamics, activation functions that are better suited to the problem of learning Lagrangians, and a physics-aware coordinate […]

Ver mais

arXiv:2601.09744v1 Announce Type: new Abstract: Industrial IoT platforms in global manufacturing environments generate continuous operational data across production assets, utilities, and connected products. While data ingestion and storage capabilities have matured significantly, enterprises continue to face systemic challenges in governing IoT data at scale. These challenges are not rooted in tooling limitations but in the absence of a governance model that aligns with the realities of distributed operational ownership, heterogeneous source systems, and continuous change at the edge. […]

Ver mais

arXiv:2601.17112v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language tasks but suffer from extremely large memory footprints and computational costs. In this paper, we introduce a tensor compression framework based on the cproduct for computing low rank approximation In the first part of our approach, we leverage the algebraic structure of the cproduct to represent weight tensors such as those in embedding layers, attention projections, and feed forward networks in […]

Ver mais

The sample complexity of multi-group learning is shown to improve in the group-realizable setting over the agnostic setting, even when the family of groups is infinite so long as it has finite VC dimension. The improved sample complexity is obtained by empirical risk minimization over the class of group-realizable concepts, which itself could have infinite VC dimension. Implementing this approach is also shown to be computationally intractable, and an alternative approach is suggested based on improper learning.

Ver mais

arXiv:2601.17076v1 Announce Type: new Abstract: Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are rife with missing views and continuously emerging classes, which pose significant obstacles to robust learning. Prevailing methods are ill-equipped for this reality, as they either lack adaptability to new classes or incur exponential parameter growth when handling all possible missing-view patterns, severely limiting their scalability in web environments. To systematically address this gap, […]

Ver mais

Until early 2025, I found LLMs pretty bad at summarizing research papers. They would miss key contributions, hallucinate details, or give generic overviews that didn’t really capture what mattered. So I mostly avoided using them for paper reading. However, models have improved significantly since then, and I’m starting to reconsider. I’ve been experimenting more recently, and the quality feels noticeably better, especially for getting a quick gist before deciding whether to deep-read something. Curious where everyone else stands: […]

Ver mais

[On agents using CLI tools in place of REST APIs] To save on context window, yes, but moreso to improve accuracy and success rate when multiple tool calls are involved, particularly when calls must be correctly chained e.g. for pagination, rate-limit backoff, and recognizing authentication failures. Other major factor: which models can wield the skill? Using the CLI lowers the bar so cheap, fast models (gpt-5-nano, haiku-4.5) can reliably succeed. Using the raw APl is something only the […]

Ver mais

arXiv:2602.15254v1 Announce Type: new Abstract: Characterizing the interdependent nature of Anthropocene systems of systems is fundamental to making informed decisions to address challenges across complex ecological, environmental, and coupled human-natural systems. This paper presents the first application of Model-Based Systems Engineering (MBSE) and Hetero-functional Graph Theory (HFGT) to economic systems, establishing a scalable and extensible methodology for integrating economic input-output (EIO) models within a unified system-of-systems modeling framework. Integrating EIO models into the MBSE-HFGT workflow demonstrates how the […]

Ver mais