arXiv:2602.00974v1 Announce Type: new Abstract: Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. Still, most existing methods rely on Euclidean geometry to model intra-domain relationships. This approach can fail when features are only weakly related to the task of interest, leading to noisy, semantically misleading structure and degraded alignment quality. To address this limitation, we introduce FoSTA (Forest-guided Semantic Transport Alignment), a scalable alignment framework that […]

Ver mais

Product teams spend enormous energy getting to launch. We know the drill—roadmaps debated for weeks, specs refined until everyone’s sick of looking at them, designs polished to pixel-perfect precision. Metrics get defined, redefined, and argued over. Finally, you ship, and the whole team exhales. That’s usually when the real work should start. Because the hardest part of product management isn’t shipping. It’s listening honestly to what happens after—and being willing to act on what you hear, even when […]

Ver mais

Given how badly burned anyone who took Apple’s 2024 WWDC Apple Intelligence announcements at face value was, I’m holding to a strict “I’ll believe it when I see it” policy for everything they announced today. The new Siri AI features do at least look feasible with today’s technology, especially since Apple are licensing a custom Gemini-derived model that they can run on their own Private Cloud Compute. It sounds like they’ll be taking advantage of vision LLMs to […]

Ver mais

arXiv:2603.08759v1 Announce Type: new Abstract: Music structure segmentation is a key task in audio analysis, but existing models perform poorly on Electronic Dance Music (EDM). This problem exists because most approaches rely on lyrical or harmonic similarity, which works well for pop music but not for EDM. EDM structure is instead defined by changes in energy, rhythm, and timbre, with different sections such as buildup, drop, and breakdown. We introduce EDMFormer, a transformer model that combines self-supervised audio […]

Ver mais

arXiv:2602.22255v1 Announce Type: new Abstract: We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space under a learned, time-dependent Hamiltonian. Unlike standard recurrent architectures that rely on gating mechanisms to suppress competing hypotheses, our framework utilizes quantum interference: the Hamiltonian steers the phases of complex amplitudes so that conflicting interpretations cancel while compatible ones reinforce. The dynamics are strictly unitary, ensuring that the state norm is […]

Ver mais

arXiv:2606.26207v1 Announce Type: new Abstract: Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, and systematic evidence remains limited. In this work, we present a systematic study of the role of input dimensionality in both the emergence and the targeted control of adversarial examples. We first analyse the scope and limitations of existing theoretical frameworks based on concentration […]

Ver mais

arXiv:2602.00986v1 Announce Type: new Abstract: In this paper, we identify a sparse reward subsystem within the hidden states of Large Language Models (LLMs), drawing an analogy to the biological reward subsystem in the human brain. We demonstrate that this subsystem contains value neurons that represent the model’s internal expectation of state value, and through intervention experiments, we establish the importance of these neurons for reasoning. Our experiments reveal that these value neurons are robust across diverse datasets, model […]

Ver mais

arXiv:2603.08816v1 Announce Type: new Abstract: This preprint presents a neural network tuner for the finite state model predictive control of an induction motor. The tuner deals with the parameters of the controllers in the speed loop and in the stator current loop. The results are assessed using a five phase machine in an experimental setup. Data for the neural network training is obtained from the experiments using step tests.

Ver mais