March 2026

First-generation stablecoins solved a real problem. They gave crypto markets a stable unit of account and made cross-border value transfer faster and cheaper than legacy systems. But they did this by keeping things simple – a token is a claim on a reserve, and the blockchain moves that claim around. The token itself carries no information about who holds it, why it is being moved, or whether the counterparties on either end are compliant with the rules that […]

Ver mais

Social media platforms generate massive streams of conversational data. For researchers and data scientists, this data provides a way to study how language shapes online interaction at scale. I built a Python pipeline to collect and analyze 16,695 Arabic tweets from X (formerly Twitter) to examine whether linguistic signals like uncertainty influence how people respond to posts. This article walks through the technical process behind the project: data collection, preprocessing, linguistic classification, and statistical analysis. Tech Stack This […]

Ver mais

Let me tell you about a code review I sat through two years into my engineering career. I had written a solution that worked. I had written a solution that worked out. It changed into readable, it turned into fast, and it solved the exact trouble we had. My senior engineer looked at it and said a few words I still think about: “That’s not best practice.” No explanation. No alternative. Just the verdict. I rewrote it the […]

Ver mais

Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce. We introduce emph{RiboSphere}, a framework that learns emph{discrete} geometric representations of RNA by combining vector quantization with flow matching. Our design is motivated by the modular organization of RNA architecture: complex folds are composed from recurring structural motifs. RiboSphere uses a geometric transformer encoder to produce SE(3)-invariant (rotation/translation-invariant) features, which are discretized with finite […]

Ver mais

Learned priors based on deep generative models offer data-driven regularization for seismic inversion, but training them requires a dataset of representative subsurface models — a resource that is inherently scarce in geoscience applications. Since the training objective of most generative models can be cast as maximum likelihood on a finite dataset, any such model risks converging to the empirical distribution — effectively memorizing the training examples rather than learning the underlying geological distribution. We show that the posterior […]

Ver mais

Conventional machine learning pipelines often struggle to recognize categories absent from the original trainingset. This gap typically reduces accuracy, as fixed datasets rarely capture the full diversity of a domain. To address this, we propose a continual learning framework for text-guided food classification. Unlike approaches that require retraining from scratch, our method enables incremental updates, allowing new categories to be integrated without degrading prior knowledge. For example, a model trained on Western cuisines could later learn to classify […]

Ver mais

arXiv:2603.07313v3 Announce Type: replace-cross Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting where an adversary selects a hidden initial latent distribution before the episode, termed an adversarial latent-initial-state POMDP. Theoretically, we prove a latent minimax principle, characterize worst-case defender distributions, and derive approximate best-response inequalities with finite-sample concentration bounds that make the optimization and sampling terms explicit. Empirically, using a Battleship benchmark, we demonstrate that targeted exposure to […]

Ver mais

arXiv:2602.06175v2 Announce Type: replace-cross Abstract: Expand-and-sparsify representations are a class of theoretical models that capture sparse representation phenomena observed in the sensory systems of many animals. At a high level, these representations map an input $x in mathbb{R}^d$ to a much higher dimension $m gg d$ via random linear projections before zeroing out all but the $k ll m$ largest entries. The result is a $k$-sparse vector in ${0,1}^m$. We study the suitability of this representation for two […]

Ver mais

arXiv:2512.23178v2 Announce Type: replace-cross Abstract: Optimization under heavy-tailed noise has become popular recently, since it better fits many modern machine learning tasks, as captured by empirical observations. Concretely, instead of a finite second moment on gradient noise, a bounded ${frak p}$-th moment where ${frak p}in(1,2]$ has been recognized to be more realistic (say being upper bounded by $sigma_{frak l}^{frak p}$ for some $sigma_{frak l}ge0$). A simple yet effective operation, gradient clipping, is known to handle this new challenge […]

Ver mais

arXiv:2510.04265v3 Announce Type: replace-cross Abstract: Pass$@k$ is widely used to report the reasoning performance of LLMs, but it often produces unstable and potentially misleading rankings, especially when the number of trials (samples) is limited and computational resources are constrained. We present a principled Bayesian evaluation framework that replaces Pass$@k$ and average accuracy over $N$ trials (avg$@N$) with posterior estimates of a model’s underlying success probability and credible intervals, yielding stable rankings and a transparent decision rule for differences. […]

Ver mais