We present an algorithm name cSAT+ for learning the causal structure in a domain from datasets measuring different variables sets. The algorithm outputs a graph with edges corresponding to all possible pairwise causal relations between two variables, named Pairwise Causal Graph (PCG). Examples of interesting inferences include the induction of the absence or presence of some causal relation between two variables never measured together. cSAT+ converts the problem to a series of SAT problems, obtaining leverage from the […]

Ver mais

Spectral bias, the tendency of neural networks to learn low frequencies first, can be both a blessing and a curse. While it enhances the generalization capabilities by suppressing high-frequency noise, it can be a limitation in scientific tasks that require capturing fine-scale structures. The delayed generalization phenomenon known as grokking is another barrier to rapid training of neural networks. Grokking has been hypothesized to arise as learning transitions from the NTK to the feature-rich regime. This paper explores […]

Ver mais

arXiv:2601.15308v1 Announce Type: new Abstract: Extended Reality (XR), including virtual, augmented, and mixed reality, provides immersive and interactive experiences across diverse applications, from VR-based education to AR-based assistance and MR-based training. However, widespread XR adoption remains limited due to two key challenges: 1) the high cost and complexity of authoring 3D content, especially for large-scale environments or complex interactions; and 2) the steep learning curve associated with non-intuitive interaction methods like handheld controllers or scripted gestures. Generative AI […]

Ver mais

How Governance Turns AI Agent Experiments into Predictable Business Outcomes 1. The Strategic Inflection Point: From AI Tools to an Autonomous Workforce As we approach 2026, enterprises worldwide face a pivotal moment – the dawn of the “agent era.” Companies are swiftly transitioning from basic generative AI applications to sophisticated autonomous systems capable of handling complex business tasks. This evolution has unveiled a critical challenge: the “paradox of increasing investment versus uncertain returns.” Despite widespread adoption, with 79% […]

Ver mais

arXiv:2509.21906v2 Announce Type: replace-cross Abstract: Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion models. However, their convergence properties and error analysis remain largely unexplored. In this work, we develop a unified framework grounded in stochastic calculus theory to systematically investigate the theoretical properties of discrete flow models. Specifically, by leveraging a Girsanov-type theorem for the path measures of two continuous-time Markov chains […]

Ver mais

arXiv:2511.23310v2 Announce Type: replace Abstract: Existing reinforcement learning (RL)-based post-training methods for large language models have advanced rapidly, yet their design has largely been guided by heuristics rather than systematic theoretical principles. This gap limits our understanding of the properties of the gradient estimators and the associated optimization algorithms, thereby constraining opportunities to improve training stability and overall performance. In this work, we provide a unified theoretical framework that characterizes the statistical properties of commonly used policy-gradient estimators […]

Ver mais

Byline: Keith Belanger AI projects have a way of surfacing data problems that data teams used to be able to work around. That’s because analytical data allowed for a wide margin of error, and AI simply doesn’t. AI models don’t tolerate ambiguity, and decisions made at machine speed magnify every flaw hiding upstream. What once failed quietly now fails loudly, and often publicly. AI failures are often dismissed as experimental growing pains. In reality, they’re revealing the weakness […]

Ver mais

The most dangerous advice in academia is “just start writing.” It sounds noble. It sounds productive. It is also a lie. Telling a graduate student to “just write” without a structure is like telling a construction crew to “just build” without a blueprint. You might end up with walls, but they won’t hold a roof. You will spend six months pouring concrete only to realize you forgot the plumbing. I see this every year. Brilliant students freeze. They […]

Ver mais

arXiv:2601.08967v1 Announce Type: new Abstract: The classical Maker-Breaker positional game is played on a board which is a hypergraph $mathcal{H}$, with two players, Maker and Breaker, alternately claiming vertices of $mathcal{H}$ until all the vertices are claimed. When the game ends, Maker wins if she has claimed all the vertices of some edge of $mathcal{H}$; otherwise, Breaker wins. Playing this game in real life can be done by placing tokens on the vertices of the board. In this […]

Ver mais