digitado

We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space from both paired and unpaired data, and (ii) performing joint distribution matching in this space via the 1-Wasserstein distance, using only paired data. This two-step approach minimizes an upper bound on the 1-Wasserstein distance between joint distributions, reducing reliance on scarce paired samples while enabling fast one-step generation. Theoretically, we […]

Ver mais

I’m behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba’s Qwen team over the past few weeks. I’m hoping that the 3.5 family doesn’t turn out to be Qwen’s swan song, seeing as that team has had some very high profile departures in the past 24 hours. It all started with this tweet from Junyang Lin (@JustinLin610): me stepping down. bye my beloved qwen. Junyang Lin was the lead researcher […]

Ver mais

Training large-scale Neural Networks requires substantial computational power and energy. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training. Various client selection strategies have been developed to align the volatility of renewable energy with stable and fair model training in a federated system. However, due to the privacy-preserving nature of Federated Learning, the quality of data on client devices remains unknown, posing challenges for […]

Ver mais

Harmful algal blooms (HABs) can threaten coastal infrastructure, fisheries, and desalination dependent water supplies. This project (REDNET-ML) develops a reproducible machine learning pipeline for HAB risk detection along the Omani coastline using multi sensor satellite data and non leaky evaluation. The system fuses (i) Sentinel-2 optical chips (high spatial resolution) processed into spectral indices and texture signals, (ii) MODIS Level-3 ocean color and thermal indicators, and (iii) learned image evidence from object detectors trained to highlight bloom like […]

Ver mais

Developing exoskeleton controllers that generalize across diverse locomotor conditions typically requires extensive motion-capture data and biomechanical labeling, limiting scalability beyond instrumented laboratory settings. Here, we present a physics-based neuromusculoskeletal learning framework that trains a hip-exoskeleton control policy entirely in simulation, without motion-capture demonstrations, and deploys it on hardware via policy distillation. A reinforcement learning teacher policy is trained using a muscle-synergy action prior over a wide range of walking speeds and slopes through a two-stage curriculum, enabling direct […]

Ver mais

A father is suing Google and Alphabet, alleging its Gemini chatbot reinforced his son’s delusional belief it was his AI wife and coached him toward suicide and a planned airport attack.

Ver mais

Formal methods are software engineering approaches with a rigorous mathematical basis that can be used in helping to ensure the correctness of software systems, especially where safety or security is critical. Artificial Intelligence (AI) has developed very rapidly in the area of Generative AI (GenAI), where questions can be answered with increasingly impressive but with potentially unreliable and variable results. This paper surveys research in integrating the two approaches in a synergistic manner. Traditionally, such explorations have required […]

Ver mais

Hi all, I’ve been working on building a Multi-Agent PPO for Mad Pod Racing on CodinGame, using a simple multi-layer perceptron for both the agents and the critic. For the input data, I have distance [0, 16000] and speed [0, 700]. I first scaled the real values by their maximums to bring them into a smaller range. With this simple scaling and short training, my agent stabilized at a mediocre performance. Then, I tried normalizing the data using […]

Ver mais