I wanted to share a project I’ve been building called Sovereign Mohawk. It’s a Go-based runtime (using Wasmtime) designed to solve the scaling and trust issues in edge-heavy federated learning. Most FL setups hit a wall at a few thousand nodes due to $O(dn)$ communication overhead and vulnerability to model poisoning. What’s different here: O(d log n) Scaling: Using a hierarchical tree-based aggregation that I’ve empirically validated up to 10M nodes. This reduced metadata overhead from ~40 TB […]

Ver mais

arXiv:2602.11166v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tuning methods affect hallucination behavior remains insufficiently understood, especially on QA datasets. In this work, we systematically investigate the impact of PEFT on hallucination detection through a comprehensive empirical study across three open-weight LLM backbones and three fact-seeking QA benchmarks. For each model, we evaluate […]

Ver mais

arXiv:2505.19712v3 Announce Type: replace-cross Abstract: This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to learning generative models by estimating velocity fields that guide transformations from a source to a target distribution. Rectified flow matching aims to straighten the learned transport paths, yielding more direct flows between distributions. Our first contribution is a set of invariance properties of rectified flows and explicit velocity fields. In addition, we also […]

Ver mais

arXiv:2510.08539v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a principled understanding of why it works is lacking. This paper builds a theoretical foundation for RLVR by analyzing its training process at both the full-response (trajectory) and token levels. Central to our analysis is a new quantity called the Gradient Gap, which formalizes the direction of improvement from low-reward to […]

Ver mais

arXiv:2601.18974v1 Announce Type: new Abstract: Traffic shaping and Quality of Service (QoS) enforcement are critical for managing bandwidth, latency, and fairness in networks. These tasks often rely on low-level traffic control settings, which require manual setup and technical expertise. This paper presents an automated framework that converts high-level traffic shaping intents in natural or declarative language into valid and correct traffic control rules. To the best of our knowledge, we present the first end-to-end pipeline that ties intent […]

Ver mais

Uncrewed Aerial Vehicles (UAVs) are increasingly used in civilian and industrial applications, making secure low-altitude operations crucial. In dense mmWave environments, accurately classifying low-altitude UAVs as either inside authorized or restricted airspaces remains challenging, requiring models that handle complex propagation and signal variability. This paper proposes a deep learning model, referred to as CoBA, which stands for integrated Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention which leverages Fifth Generation (5G) millimeter-wave (mmWave) radio measurements […]

Ver mais

Offline policy learning aims to use historical data to learn an optimal personalized decision rule. In the standard estimate-then-optimize framework, reweighting-based methods (e.g., inverse propensity weighting or doubly robust estimators) are widely used to produce unbiased estimates of policy values. However, when the propensity scores of some treatments are small, these reweighting-based methods suffer from high variance in policy value estimation, which may mislead the downstream policy optimization and yield a learned policy with inferior value. In this […]

Ver mais

Although I still hope things will go differently, the experts I’ve spoken to think we are likely to face a global tragedy—hundreds of thousands of deaths from Covid-19. I hope that society views this as a warning for the future.  Covid-19 is bad, but only a warm-up.  I think it’s unlikely that this is the worst new pandemic (human-created or otherwise) we’ll see in our lifetimes.  We need to be ready to deal with it much better next […]

Ver mais