arXiv:2602.12683v2 Announce Type: replace-cross Abstract: We reformulate Optimal Transport Conditional Flow Matching (OT-CFM), a class of dynamical generative models, showing that it admits an exact proximal formulation via an extended Brenier potential, without assuming that the target distribution has a density. In particular, the mapping to recover the target point is exactly given by a proximal operator, which yields an explicit proximal expression of the vector field. We also discuss the convergence of minibatch OT-CFM to the population […]

Ver mais

If you apply what’s on this email to the T, you can rebuild yourself in six months. Bold statement? Yes. But give me a few minutes and I’ll gift you the EXACT blueprint for: A different body. A different mind. A different baseline of energy. A different standard for what you tolerate. A different life altogether. And this is not manifestation. This is engineering, and this is what we do here. We will work on: identity, body, skills, environment, […]

Ver mais

The equations of complex dynamical systems may not be identified by expert knowledge, especially if the underlying mechanisms are unknown. Data-driven discovery methods address this challenge by inferring governing equations from time-series data using a library of functions constructed from the measured variables. However, these methods typically assume time-invariant coefficients, which limits their ability to capture evolving system dynamics. To overcome this limitation, we allow some of the parameters to vary over time, learn their temporal evolution directly […]

Ver mais

arXiv:2602.05010v1 Announce Type: new Abstract: In the real world, robots frequently make errors, yet little is known about people’s social responses to errors outside of lab settings. Prior work has shown that social signals are reliable and useful for error management in constrained interactions, but it is unclear if this holds in the real world – especially with a non-social robot in repeated and group interactions with successive or propagated errors. To explore this, we built a coffee […]

Ver mais

arXiv:2604.03218v1 Announce Type: cross Abstract: Suppose we observe data from a distribution $P$ and we wish to test the composite null hypothesis that $Pinmathscr P$ against a composite alternative $Pin mathscr Qsubseteq mathscr P^c$. Herbert Robbins and coauthors pointed out around 1970 that, while no batch test can have a level $alphain(0,1)$ and power equal to one, sequential tests can be constructed with this fantastic property. Since then, and especially in the last decade, a plethora of sequential […]

Ver mais

arXiv:2603.10047v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs) are outputs that are syntactically coherent but factually incorrect or contextually inconsistent. They are persistent obstacles in high-stakes industrial settings such as engineering design, enterprise resource planning, and IoT telemetry platforms. We present and compare five prompt engineering strategies intended to reduce the variance of model outputs and move toward repeatable, grounded results without modifying model weights or creating complex validation models. These methods include: (M1) Iterative […]

Ver mais

arXiv:2601.00126v2 Announce Type: new Abstract: Generative models have emerged as powerful tools for planning, with compositional approaches offering particular promise for modeling long-horizon task distributions by composing together local, modular generative models. This compositional paradigm spans diverse domains, from multi-step manipulation planning to panoramic image synthesis to long video generation. However, compositional generative models face a critical challenge: when local distributions are multimodal, existing composition methods average incompatible modes, producing plans that are neither locally feasible nor globally […]

Ver mais