digitado

Update on MH-FLOCKE. This version brought two things: a 60% SNN speedup and a neural CPG to replace the sine waves. Long nights. The speedup came from wrapping the SNN step in torch.no_grad(), switching to dense matmul for small networks, and caching time constants. The 232-neuron Freenove SNN now runs at 1.2ms/step in simulation. Along the way I found that setting output neurons to Fast Spiking (Izhikevich a=0.1) destabilized the Go2 — motoneurons are biologically Regular Spiking, not […]

Ver mais

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that searches for adversarial inputs within the continuous embedding space of LLMs during AT. While CAT has achieved empirical success, its underlying mechanism, i.e., why adversarial perturbations in the embedding space can help LLMs defend against jailbreak prompts synthesized in the input […]

Ver mais

Federated learning (FL) is a distributed paradigm that coordinates massive local clients to collaboratively train a global model via stage-wise local training processes on the heterogeneous dataset. Previous works have implicitly studied that FL suffers from the “client-drift” problem, which is caused by the inconsistent optimum across local clients. However, till now it still lacks solid theoretical analysis to explain the impact of this local inconsistency. To alleviate the negative impact of “client drift” and explore its substance […]

Ver mais

If you know the distance d to a satellite, you can compute a circle of points that passes through your location. That’s because you’re at the intersection of two spheres—the earth’s surface and a sphere of radius d centered on the satellite—and the intersection of two spheres is a circle. Said another way, one observation of a satellite determines a circle of possible locations. If you know the distance to a second satellite as well, then you can […]

Ver mais

In 1986 the US Food and Drug Administration issued its first approval for human use of a therapeutic antibody. Despite steady advances in methodology, genetic sequencing, and biomedical science, 40 years later the process of discovering and optimizing therapeutic antibodies often remains prohibitively expensive, in terms of both cost and time. Recent experiences with pandemic-style infectious-disease outbreaks lend an even greater urgency to the need to more quickly and efficiently identify and develop these antibodies. Artificial-intelligence- and machine-learning-guided […]

Ver mais

We describe the evolution of DEMOCRITUS, a system for inferring causality from language. Extracting causal claims from natural language is unstable under paraphrase granularity shifts, and context drift. A document collection may express the same causal statement in many surface forms, while neighboring studies may agree locally yet fail to glue globally because relation families or polarities change across regimes. This paper studies that problem through successive versions of DEMOCRITUS, an implemented system for compiling documents into local […]

Ver mais

The Automatic Identification System (AIS) generates massive volumes of real-world ship trajectory data, providing a critical foundation for maritime ship type classification. However, existing methods often struggle to simultaneously capture long-range temporal dependencies, maintain computational efficiency, and ensure model interpretability, which makes accurate multi-class classification challenging in real-world maritime environments. To address these limitations, this study proposes a robust and efficient hybrid framework. The proposed architecture integrates a Feature Transformer module for deep temporal feature extraction with a […]

Ver mais

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense mechanism against MIAs in FL, leveraging the environment of the 2025 NIST Genomics Privacy-Preserving Federated Learning (PPFL) Red Teaming Event. To improve inference accuracy, we propose a stacking attack strategy that ensembles seven black-box estimators to train a meta-classifier on prediction probabilities and cross-entropy losses. We […]

Ver mais

In recent years, Sound AI is being increasingly used to predict machine failures. By attaching a microphone to the machine of interest, one can get real time data on machine behavior from the field. Traditionally, Convolutional Neural Net (CNN) architectures have been used to analyze spectrogram images generated from the sounds captured and predict if the machine is functioning as expected. CNN architectures seem to work well empirically even though they have biases like locality and parameter-sharing which […]

Ver mais

Load testing is a critical component of performance engineering, but traditional script-based methodologies often fail to accurately represent the dynamic, stochastic behavior of real users in modern distributed systems. As web applications grow in complexity, linear testing sequences leave critical execution paths untested, obscuring concurrency bottlenecks. This paper proposes a hybrid conceptual framework that integrates probabilistic navigation graphs with Markov transition models to simulate realistic, chaotic user behavior. The proposed model represents application workflows as directed graphs, employing […]

Ver mais