After spending time on quantitative strategies, I’ve realized that relying on a single signal rarely works in all market conditions. Momentum indicators perform well in trending markets, but they can fail completely in sideways movements. Recently, I shifted my focus from “finding the best signal” to “how signals work together.” My latest experiment combines momentum, volatility, and trend strength factors to see how they interact and how the combined strategy performs. Before diving in, I had to tackle […]

Ver mais

If you’ve been following any entertainment media at all, you probably know it’s time for the Coachella Valley Music and Arts Festival, a massive two-weekend music festival held at the Empire Polo Club in Indio, California. We are approaching the second weekend of Coachella 2026, featuring headliners such as Sabrina Carpenter (Friday), Justin Bieber (Saturday), and Karol G (Sunday). It sold out in 3 hours with about 240,000 tickets sold for the two weekends. In 2022, Coachella partnered […]

Ver mais

arXiv:2603.20538v1 Announce Type: cross Abstract: Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably effective, from large language models (LLMs) to vision-language-action systems (VLAs). However, applying autoregressive models to continuous control requires discretizing actions through quantization, a practice widely adopted yet poorly understood theoretically. This paper provides theoretical foundations for this practice. We analyze how quantization error propagates […]

Ver mais

You may come across a programming task where you want to implement the following pattern: try this and, if it doesn’t work out, try the other thing. In other words, you want a computation composed of two (or more) alternatives which should be tried one after the other until one of them produces a useful result. As an example, let’s build a function that takes a String as input and returns Just String if that input is either […]

Ver mais

Automation underpins progress across scientific and industrial disciplines. Yet, automating tasks requiring interpretation of abstract visual information remain challenging. For example, crystal alignment strongly relies on humans with the ability to comprehend diffraction patterns. Here we introduce an autonomous system that aligns single crystals without access to crystallography and diffraction theory. Using a model-free reinforcement learning framework, an agent learns to identify and navigate towards high-symmetry orientations directly from Laue diffraction patterns. Despite the absence of human supervision, […]

Ver mais

arXiv:2603.26786v1 Announce Type: new Abstract: The rapid evolution of Multimodal Large Language Models (MLLMs) is bottlenecked by the saturation of high-quality public data, while vast amounts of diverse multimodal data remain inaccessible in privacy-sensitive silos. Federated Learning (FL) offers a promising solution to unlock these distributed resources, but existing research focuses predominantly on fine-tuning, leaving the foundational pre-training phase largely unexplored. In this paper, we formally introduce the Federated MLLM Alignment (Fed-MA) task, a lightweight pre-training paradigm that […]

Ver mais

arXiv:2602.11185v1 Announce Type: new Abstract: Gradient signals in LLM training are highly anisotropic: recurrent linguistic structure concentrates energy into a small set of dominant spectral directions, while context specific information resides in a long tail. We show that this spike tail separation persists throughout training, with the spike occupying only about 1.5% of directions yet dominating optimizer statistics. This dominance suppresses tail learning by contracting tail updates through second moment normalization and tightening the globally stable learning rate […]

Ver mais

On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy and policy updates must be conservative. In this paper, we revisit policy representation as a first-class design choice for on-policy optimization. We study discretized categorical actors that represent each action dimension with a distribution over bins, yielding a policy objective that resembles a cross-entropy loss. Building […]

Ver mais

Recent advances in query optimization have shifted from traditional rule-based and cost-based techniques towards machine learning-driven approaches. Among these, reinforcement learning (RL) has attracted significant attention due to its ability to optimize long-term performance by learning policies over query planning. However, existing RL-based query optimizers often exhibit unstable performance at the level of individual queries, including severe performance regressions, and require prolonged training to reach the plan quality of expert, cost-based optimizers. These shortcomings make learned query optimizers […]

Ver mais