Embeddings provide low-dimensional representations that organize complex function spaces and support generalization. They provide a geometric representation that supports efficient retrieval, comparison, and generalization. In this work we generalize the concept to Physics Informed Neural Networks. We present a method to construct solution embedding spaces of nonlinear partial differential equations using a multi-head setup, and extract non-degenerate information from them using principal component analysis (PCA). We test this method by applying it to viscous Burgers’ equation, which is […]

Ver mais

arXiv:2604.02390v1 Announce Type: new Abstract: Audio-visual navigation tasks require agents to locate and navigate toward continuously vocalizing targets using only visual observations and acoustic cues. However, existing methods mainly rely on simple feature concatenation or late fusion, and lack an explicit discrete representation of the target’s relative position, which limits learning efficiency and generalization. We propose Spatial-Aware Conditioned Fusion (SACF). SACF first discretizes the target’s relative direction and distance from audio-visual cues, predicts their distributions, and encodes them […]

Ver mais

arXiv:2603.25397v1 Announce Type: cross Abstract: In this applied paper, we address the difficult open problem of when to discharge patients from the Intensive Care Unit. This can be conceived as an optimal stopping scenario with three added challenges: 1) the evaluation of a stopping strategy from observational data is itself a complex causal inference problem, 2) the composite objective is to minimize the length of intervention and maximize the outcome, but the two cannot be collapsed to a […]

Ver mais

Modern sci-fi isn’t predicting the future—it’s exposing the structural failures already baked into governance, AI, and sovereignty systems. From VC-owned states to opaque black boxes and unforkable institutions, the real threat isn’t technology, but who controls it and whether people retain the right to exit, audit, and rebuild.

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

Elon Musk spent the better part of three days on the witness stand this week in his lawsuit against OpenAI, and it’s already getting messy. Emails, texts, and his own tweets are surfacing in court, and there are plenty more witnesses to come. Musk’s argument against OpenAI? By converting the company to a for-profit model, Sam Altman betrayed the “nonprofit for the […]

Ver mais

arXiv:2603.00651v1 Announce Type: new Abstract: Dataset pruning has been widely studied for 2D images to remove redundancy and accelerate training, while particular pruning methods for 3D data remain largely unexplored. In this work, we study dataset pruning for 3D data, where its observed common long-tail class distribution nature make optimization under conventional evaluation metrics Overall Accuracy (OA) and Mean Accuracy (mAcc) inherently conflicting, and further make pruning particularly challenging. To address this, we formulate pruning as approximating the […]

Ver mais

arXiv:2512.06945v2 Announce Type: replace Abstract: Access to multiple predictive models trained for the same task, whether in regression or classification, is increasingly common in many applications. Aggregating their predictive uncertainties to produce reliable and efficient uncertainty quantification is therefore a critical but still underexplored challenge, especially within the framework of conformal prediction (CP). While CP methods can generate individual prediction sets from each model, combining them into a single, more informative set remains a challenging problem. To address […]

Ver mais

arXiv:2604.16949v1 Announce Type: new Abstract: The paper considers the computation of L1 regularization paths in a state space setting, which includes L1 regularized Kalman smoothing, linear SVM, LASSO, and more. The paper proposes two new algorithms, which are duals of each other; the first algorithm applies to L1 regularization of independent variables while the second applies to L1 regularization of dependent variables. The heart of the proposed algorithms is parametric Gaussian message passing (i.e., Kalman-type forward-backward recursions) in […]

Ver mais

A 30-year-old Danish entrepreneur is building Southeast Asia’s answer to Hims & Hers. Launched in the Philippines, &you offers private online doctor consultations and discreet medication delivery. By focusing on speed, privacy, and cultural trust, the startup aims to fix healthcare access gaps and reach unicorn status within three years.

Ver mais