Modern software delivery depends on the reliability, integrity, and security of container images. As organisations migrate to microservices, automated CI/CD pipelines, and multi-cloud architectures, the container image becomes more than a packaging mechanism, it becomes a security boundary. A single vulnerability embedded in an image can replicate in clusters, environments, and deployments, creating widespread risk for applications that rely on speed and repeatability. Security-forward organisations are increasingly shifting from general-purpose base images to secure-by-design, minimal, or enterprise-maintained images […]

Ver mais

In imitation learning, robots are supposed to learn from demonstrations of the desired behavior. Most of the work in imitation learning for swarm robotics provides the demonstrations as rollouts of an existing policy. In this work, we provide a framework based on generative adversarial imitation learning that aims to learn collective behaviors from human demonstrations. Our framework is evaluated across six different missions, learning both from manual demonstrations and demonstrations derived from a PPO-trained policy. Results show that […]

Ver mais

We introduce Parallel Coordinated Reasoning (PaCoRe), a training-and-inference framework designed to overcome a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. PaCoRe departs from the traditional sequential paradigm by driving TTC through massive parallel exploration coordinated via a message-passing architecture in multiple rounds. Each round launches many parallel reasoning trajectories, compacts their findings into context-bounded messages, and synthesizes these messages to guide the next […]

Ver mais

arXiv:2603.03785v1 Announce Type: new Abstract: Randomized Controlled Trials (RCTs) represent the gold standard for causal inference yet remain a scarce resource. While large-scale observational data is often available, it is utilized only for retrospective fusion, and remains discarded in prospective trial design due to bias concerns. We argue this “tabula rasa” data acquisition strategy is fundamentally inefficient. In this work, we propose Active Residual Learning, a new paradigm that leverages the observational model as a foundational prior. This […]

Ver mais

arXiv:2602.15860v1 Announce Type: new Abstract: Current neural reranking approaches for retrieval-augmented generation (RAG) rely on cross-encoders or large language models (LLMs), requiring substantial computational resources and exhibiting latencies of 3-5 seconds per query. We propose Maniscope, a geometric reranking method that computes geodesic distances on k-nearest neighbor (k-NN) manifolds constructed over retrieved document candidates. This approach combines global cosine similarity with local manifold geometry to capture semantic structure that flat Euclidean metrics miss. Evaluating on eight BEIR benchmark […]

Ver mais

When the bubble bursts, it will be the indestructible code programmers who will learn to use these tools and new languages, but who also have the discipline required to deploy all these operations at scale. AI adoption numbers are impressive; 78% of global companies use AI in their daily operations, and 90% are exploring it. While some experts, such as Nobel Prize winner Joel Mokyr, say it has a very positive impact on economic growth, by helping people […]

Ver mais

I’m no ML expert, but a master’s student working on computational mechanics, PDEs and some deep learning for these topics. I have been following some groups, papers and trends and it is still unclear what is the exact direction in which AI4PDEs and scientific ML is going into. Recent works show reinforcement learning for fluid dynamics, neural operators applied to irregular domains via transformers, GNNs or PointNet, nice works on diffusion or flow matching for inverse problems with […]

Ver mais

Swedish vibe-coding unicorn Lovable crossed $400 million in annual recurring revenue (ARR) in February.

Ver mais

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic design. In this study, we find that one such reason lies in the distribution shift across training domains. A large degree of distribution shift can lead to better performance even under ERM. Specifically, we derive several theoretical and empirical findings demonstrating that distribution shift plays a crucial role in model […]

Ver mais