Recent advances in diffusion language models (DLMs) have presented a promising alternative to traditional autoregressive large language models (LLMs). However, DLMs still lag behind LLMs in reasoning performance, especially as the number of denoising steps decreases. Our analysis reveals that this shortcoming arises primarily from the independent generation of masked tokens across denoising steps, which fails to capture the token correlation. In this paper, we define two types of token correlation: intra-sequence correlation and inter-sequence correlation, and demonstrate that enhancing these correlations improves reasoning performance. To this end, we propose a Multi-Reward Optimization (MRO) approach, which encourages DLMs to consider the token correlation during the denoising process. More specifically, our MRO approach leverages test-time scaling, reject sampling, and reinforcement learning to directly optimize the token correlation with multiple elaborate rewards. Additionally, we introduce group step and importance sampling strategies to mitigate reward variance and enhance sampling efficiency. Through extensive experiments, we demonstrate that MRO not only improves reasoning performance but also achieves significant sampling speedups while maintaining high performance on reasoning benchmarks.

--In this work we revisit the Mobility Robustness Optimisation (MRO) algorithm and study the possibility of learning the optimal Cell Individual Offset tuning using offline Reinforcement Learning. Such methods make use of collected offline datasets to learn the optimal policy, without further exploration. We adapt and apply a sequence-based method called Decision Transformers as well as a value-based method called Conservative Q-Learning to learn the optimal policy for the same target reward as the vanilla rule-based MRO. The same input features related to failures, ping-pongs, and other handover issues are used. Evaluation for realistic New Radio networks with 3500 MHz carrier frequency on a traffic mix including diverse user service types and a specific tunable cell-pair shows that offline-RL methods outperform rule-based MRO, offering up to 7% improvement. Furthermore, offline-RL can be trained for diverse objective functions using the same available dataset, thus offering operational flexibility compared to rule-based methods. Self-Organizing Network (SON) functionalities have become key aspects of modern cellular networks for automation. They make use of collected data to allow the network to self-configure, self-optimize, and self-heal. Mobility Robustness Optimization (MRO) is the related SON feature whose aim is to optimize the configuration of relevant mobility parameters and allow users to experience seamless connectivity.

Metacontrol [6] is a framework that incorporates systems with the capability to self-adapt to maintain their functionalities at an Self-adaptation can be used in robotics to increase system robustness expected performance. Metacontrol has the design goals of being and reliability. This work describes the Metacontrol method reusable and extensible. This is achieved with the design principles: for self-adaptation in robotics. Particularly, it details how the MROS (1) separating the adaptation and application reasoning; (2) exploiting (Metacontrol for ROS Systems) framework implements and packages at runtime the engineering knowledge of how the system is Metacontrol, and it demonstrate how MROS can be applied in designed to reason how and when the system needs to adapt, i.e., a navigation scenario where a mobile robot navigates in a factory by being model-based.

In this paper, we consider learning scenarios where the learned model is evaluated under an unknown test distribution which potentially differs from the training distribution (i.e. distribution shift). The learner has access to a family of weight functions such that the test distribution is a reweighting of the training distribution under one of these functions, a setting typically studied under the name of Distributionally Robust Optimization (DRO). We consider the problem of deriving regret bounds in the classical learning theory setting, and require that the resulting regret bounds hold uniformly for all potential test distributions. We show that the DRO formulation does not guarantee uniformly small regret under distribution shift. We instead propose an alternative method called Minimax Regret Optimization (MRO), and show that under suitable conditions this method achieves uniformly low regret across all test distributions. We also adapt our technique to have stronger guarantees when the test distributions are heterogeneous in their similarity to the training data. Given the widespead optimization of worst case risks in current approaches to robust machine learning, we believe that MRO can be a strong alternative to address distribution shift scenarios.

There's a lot of buzz around Artificial Intelligence and Machine Learning, as supply chain leaders look for the killer app within their organizations.

So it seems only right that a similarly sentimental picture of NASA's Curiosity rover appears to show another pale blue dot in action--thanks to exaggerated color, anyway. The intrepid space explorer, which will celebrate its fifth anniversary on Mars in August, is roughly the size of a car. But the Mars Reconnaissance Orbiter (MRO) is nearly 200 miles above the red planet's surface, so Curiosity looks oh-so-smol. For some of you, this may just look like a really-not-great photo of a space robot. After all, we see close-up selfies of Curiosity all the time.