digitado

arXiv:2604.14160v1 Announce Type: new Abstract: The rapid digitization of nuclear power plant main control rooms has fundamentally reshaped operator interaction patterns, introducing complex soft-control behaviors and elevated cognitive risks that are not adequately addressed by existing human reliability analysis approaches. Although recent advances in large language models and autonomous agents offer new opportunities for intelligent decision support, their deployment in safety critical environments remains constrained by risks of hallucinated reasoning and weakened human authority. This study proposes NuHF […]

Ver mais

arXiv:2604.14159v1 Announce Type: new Abstract: Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce personalized text. While lightweight large language models (LLMs) make on-device auxiliary generation feasible, enabling deeply personalized, privacy-preserving, and real-time generative IMEs poses fundamental challenges.To this end, we present HUOZIIME, a personalized on-device IME powered by LLM. We endow HUOZIIME with initial human-like prediction ability by post-training a base LLM on […]

Ver mais

arXiv:2604.14158v1 Announce Type: new Abstract: Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the multifaceted nature of complex memory systems, such as dynamic state tracking and hierarchical reasoning in continuous interactions. To overcome these limitations, we propose MemGround, a rigorous long-term memory benchmark natively grounded in rich, gamified interactive scenarios. To systematically assess these capabilities, MemGround introduces a three-tier hierarchical framework that evaluates Surface State Memory, […]

Ver mais

arXiv:2604.14156v1 Announce Type: new Abstract: Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial compression, while prompt-compression methods reduce latency by removing redundant input tokens. However, these two directions remain largely separate. Most model-compression methods are static and optimized offline, and they do not exploit the fact that different prompts and decoding steps […]

Ver mais

arXiv:2604.14152v1 Announce Type: new Abstract: Ambient AI “scribe” systems promise to reduce clinical documentation burden, but automatic speech recognition (ASR) errors can remain unnoticed without careful review, and high-quality human reference transcripts are often unavailable for calibrating uncertainty. We investigate whether cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal to prioritize human verification in medical transcription workflows. Using 50 publicly available medical education audio clips (8 h 14 min), we transcribed each clip […]

Ver mais

Bitcoin’s consensus mechanism asks: Did you demonstrate sufficient computational commitment to deserve validating this block? Proof of Usefulness asks: Does this project create demonstrable value in the world? The architectural goal is the same in both cases — produce a score that cannot be easily faked and that correlates with something real. The difference is what “something real” means. In Bitcoin, it means electricity burned. In Proof of Usefulness, it means people helped.

Ver mais

In this tutorial, we explore how to run OpenAI’s open-weight GPT-OSS models in Google Colab with a strong focus on their technical behavior, deployment requirements, and practical inference workflows. We begin by setting up the exact dependencies needed for Transformers-based execution, verifying GPU availability, and loading openai/gpt-oss-20b with the correct configuration using native MXFP4 quantization, torch.bfloat16 activations. As we move through the tutorial, we work directly with core capabilities such as structured generation, streaming, multi-turn dialogue handling, tool […]

Ver mais

While modern representation learning relies heavily on global error signals, decentralized algorithms driven by local interactions offer a fundamental distributed alternative. However, the macroscopic convergence properties of these discrete dynamics on continuous data manifolds remain theoretically unresolved, notoriously suffering from parameter explosion. We bridge this gap by formalizing decentralized learning as a coupled slow-fast dynamical system on Riemannian manifolds. First, using measure-theoretic limits, we prove that the discrete spatial transitions converge uniformly to an overdamped Langevin stochastic differential […]

Ver mais

Agentic Engineering Patterns > Here’s an example of a deceptively short prompt that got a quite a lot of work done in a single shot. First, some background. I send out a free Substack newsletter around once a week containing content copied-and-pasted from my blog. I’m effectively using Substack as a lightweight way to allow people to subscribe to my blog via email. I generate the newsletter with my blog-to-newsletter tool – an HTML and JavaScript app that […]

Ver mais

How LLMesh turns your existing machines into a distributed inference mesh, and why we stopped caring about which model won. Every developer building with local LLMs hits the same wall. You run Ollama on your laptop. It works. You have a colleague with an NVIDIA box running Mistral. That works too. But your app points at localhost:11434, and when you push to staging, it breaks. So you start hardcoding IPs, writing wrapper scripts, and wishing someone had solved […]

Ver mais