In this tutorial, we implement an end-to-end Practical Byzantine Fault Tolerance (PBFT) simulator using asyncio. We model a realistic distributed network with asynchronous message passing, configurable delays, and Byzantine nodes that intentionally deviate from the protocol. By explicitly implementing the pre-prepare, prepare, and commit phases, we explore how PBFT achieves consensus under adversarial conditions while respecting the theoretical 3f+1 bound. We also instrument the system to measure consensus latency and success rates as the number of malicious nodes […]

Ver mais

arXiv:2602.09113v1 Announce Type: new Abstract: Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors — model size and family, speculative decoding strategies, and dataset characteristics — influence the energy optimizations.

Ver mais

Hi everyone, I’m currently training a small language model to improve its accuracy on code execution prediction (i.e., predicting the exact output from the code and input). I’m working with the Qwen3-4B model and have been using GRPO for training. By combining various dense reward signals, I was able to increase the accuracy to around 72%. This approach also helped eliminate the infinite Repeat Curse(a common problem in smaller Qwen models), and overall training has been stable and […]

Ver mais

Recursive (looped) Transformers decouple computational depth from parameter depth by repeatedly applying shared layers, providing an explicit architectural primitive for iterative refinement and latent reasoning. However, early looped Transformers often underperform non-recursive baselines of equal compute. While recent literature has introduced more effective recursion mechanisms to mitigate this gap, existing architectures still operate at a fixed, full-token resolution, neglecting the potential efficiency of computing over compressed latent representations. In this paper, we propose SpiralFormer, a looped Transformer that […]

Ver mais

arXiv:2603.00588v1 Announce Type: new Abstract: Efficient representation learning is essential for optimal information storage and classification. However, it is frequently overlooked in artificial neural networks (ANNs). This neglect results in networks that can become overparameterized by factors of up to 13, increasing redundancy and energy consumption. As the demand for large language models (LLMs) and their scale increase, these issues are further highlighted, raising significant ethical and environmental concerns. We analyze our previously developed biologically inspired learning rule […]

Ver mais

arXiv:2603.00541v1 Announce Type: cross Abstract: Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable hyperparameter (HP) transfer across model sizes. While maximal update parameterization ($mu$P) has provided a principled solution to both problems for width scaling, existing extensions to the joint width-depth scaling regime remain fragmented, architecture- and optimizer-specific, and often rely on technically involved theories. In this work, we develop a simple and unified spectral framework […]

Ver mais

Enterprise AI has moved from isolated prototypes to systems that shape real decisions: drafting customer responses, summarising internal knowledge, generating code, accelerating research, and powering agent workflows that can trigger actions in business systems. That creates a new security surface, one that sits between people, proprietary data, and automated execution. AI security tools exist to make those questions operational. Some focus on governance and discovery. Others harden AI applications and agents at runtime. Some emphasise testing and red […]

Ver mais

Modern insurance organizations have adopted artificial intelligence in narrow, task-specific roles, resulting in fragmented systems that optimize isolated functions without fundamentally reshaping the underwriting and claims lifecycle. This “incrementalism” yields a human-default, sequential process plagued by structural bottlenecks, inconsistent risk evaluation, and limited transparency. This paper introduces NEXUS (Next-Generation Executive Underwriting and Settlement Intelligence), a framework to re-architect insurance as an AI-native system. NEXUS transitions AI from a peripheral tool to the primary orchestrator of end-to-end processes, conceptualizing […]

Ver mais