March 2026

Why Smart Machines are Still Idiots The current AI race is obsessed with a singular, I would argue, flawed metric: Scale. AI top dogs assume that if we feed the machine more tokens, more parameters, and more compute, it will eventually “wake up” or at least become more capable than humane units. But that’s just a trap if not an illusion, as we are building the world’s most sophisticated library, yet we expect it to act like a […]

Ver mais

Short answer: Crypto ETFs are like a crypto representation on traditional stock exchanges. For the long answer, we can start with ETFs themselves. Short for Exchange-Traded Funds (ETFs), they’re centralized financial tools created around 1989, and they had nothing to do with crypto until more recently. As a type of investment fund, it pools money from many investors and uses it to track the price of something. It could be stock market indexes such as S&P500, commodities, such […]

Ver mais

Multi-agent reinforcement learning (MARL) is increasingly used to design learning-enabled agents that interact in shared environments. However, training MARL algorithms in general-sum games remains challenging: learning dynamics can become unstable, and convergence guarantees typically hold only in restricted settings such as two-player zero-sum or fully cooperative games. Moreover, when agents have heterogeneous and potentially conflicting preferences, it is unclear what system-level objective should guide learning. In this paper, we propose a new MARL pipeline called Near-Potential Policy Optimization […]

Ver mais

I wrote an article talking about (in my opinion!) the 5 best batsuits from Batman: Arkham Knight. After I finished writing it, it got me thinking of another superhero videogame centered on someone who has decades of stories, tv shows, and movies to take suit inspiration from. I’m, of course, referring to Marvel’s Spider-Man. That game had a ton of alternate costumes, a lot of them amazing, and a lot of them not so much. But today, let’s […]

Ver mais

Extreme weather events and cyberattacks can cause component failures and disrupt the operation of power distribution networks (DNs), during which reconfiguration and load shedding are often adopted for resilience enhancement. This study introduces a topology-aware graph reinforcement learning (RL) framework for outage management that embeds higher-order topological features of the DN into a graph-based RL model, enabling reconfiguration and load shedding to maximize energy supply while maintaining operational stability. Results on the modified IEEE 123-bus feeder across 300 […]

Ver mais

In practical data-driven applications on electrical equipment fault diagnosis, training data can be poisoned by sensor failures, which can severely degrade the performance of machine learning (ML) models. However, once the ML model has been trained, removing the influence of such harmful data is challenging, as full retraining is both computationally intensive and time-consuming. To address this challenge, this paper proposes a SISA (Sharded, Isolated, Sliced, and Aggregated)-based machine unlearning (MU) framework for power transformer inter-turn short-circuit fault […]

Ver mais

Quadruped locomotion provides a natural setting for understanding when model-free learning can outperform model-based control design, by exploiting data patterns to bypass the difficulty of optimizing over discrete contacts and the combinatorial explosion of mode changes. We give a principled analysis of why imitation learning with quadrupeds can be inherently effective in a small data regime, based on the structure of its limit cycles, Poincaré return maps, and local numerical properties of neural networks. The understanding motivates a […]

Ver mais

Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations. However, existing vision-language models (VLMs) frequently struggle to generalize on unseen charts because it requires abstract, symbolic, and quantitative reasoning over structured visual representations. In this work, we introduce Chart-RL, an effective reinforcement learning (RL) method that employs mathematically verifiable rewards to enhance chart question answering in VLMs. Our experiments demonstrate that Chart-RL consistently outperforms supervised fine-tuning […]

Ver mais

Many distributional quantities in reinforcement learning are intrinsically joint across actions, including distributions of gaps and probabilities of superiority. However, the classical Markov decision process (MDP) formalism specifies only marginal laws and leaves the joint law of counterfactual one-step outcomes across multiple possible actions at a state unspecified. We study coupled-dynamics environments with a multi-action generative interface which can sample counterfactual one-step outcomes for multiple actions under shared exogenous randomness. We propose joint MDPs (JMDPs) as a formalism […]

Ver mais