This creates a tight feedback loop between representation learning,memory,reinforcementlearning,andsampling-basedplanning.

Our method achieves advanced partialto-partial non-rigid point cloud registration results onthe4DMatch/4DLoMatch benchmark under both no-learned and supervised settings.

The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces such as torque, joint angle, or end-effector position. This forces the agent to make decision at each point in training, and hence, limit the scalability to continuous, high-dimensional,andlong-horizontasks.Incontrast,researchinclassicalrobotics has, for a long time, exploited dynamical systems as a policy representation to learn robot behaviors via demonstrations.

Meta-learning methods for regression like Neural (Diffusion) Processes achieve impressive results, but with these models it can be difficult to incorporate expert prior knowledge and information contained in metadata. Large Language Models (LLMs) are trained on giant corpora including varied real-world regression datasets alongside their descriptions and metadata, leading to impressive performance on a range of downstream tasks. Recent work has extended this to regression tasks and is able to leverage such prior knowledge and metadata, achieving surprisingly good performance, but this still rarely matches dedicated meta-learning methods. Here we introduce a general method for sampling from a product-of-experts of a diffusion or flow matching model and an `expert' with binned probability density; we apply this to combine neural diffusion processes with LLM token probabilities for regression (which may incorporate textual knowledge), exceeding the empirical performance of either alone.

Mixture-of-Experts (MoE) models scale large language models through conditional computation, but inference becomes memory-bound once expert weights exceed the capacity of GPU memory. In this case, weights must be offloaded to external memory, and fetching them incurs costly and repeated transfers. We address this by adopting CXL-attached near-data processing (CXL-NDP) as the offloading tier to execute cold experts in place, converting expensive parameter movement into cheaper activation movement. Unlike prior GPU-NDP systems that are largely context-agnostic and reactive, we develop a context-aware MoE system that uses prefill-stage activation statistics to guide decoding-stage expert placement, dynamically pins hot experts in GPU-side HBM, and maps the remainder to CXL-NDP. To meet NDP's limited compute throughput, we introduce context-aware mixed-precision quantization that allocates per-expert bitwidths (1-4 bit) based on prefill stage. The resulting MoE inference system overlaps GPU and NDP execution while minimizing cross-device movement. The evaluation on the GPU-NDP system shows that our approach achieves up to an 8.7-fold decoding throughput improvement over the state-of-the-art method, while incurring only a 0.13% average accuracy drop.

Uncertainty-aware wind power prediction is essential for grid integration and reliable wind farm operation. We apply neural diffusion processes (NDPs)--a recent class of models that learn distributions over functions--and extend them to a multi-task NDP (MT-NDP) framework for wind power prediction. We provide the first empirical evaluation of NDPs in real supervisory control and data acquisition (SCADA) data. We introduce a task encoder within MT-NDPs to capture cross-turbine correlations and enable few-shot adaptation to unseen turbines. The proposed MT-NDP framework outperforms single-task NDPs and GPs in terms of point accuracy and calibration, particularly for wind turbines whose behaviour deviates from the fleet average. In general, NDP-based models deliver calibrated and scalable predictions suitable for operational deployment, offering sharper, yet trustworthy, predictive intervals that can support dispatch and maintenance decisions in modern wind farms. Introduction Wind energy has become a cornerstone of the global transition to clean power. As wind power capacity expands worldwide, ensuring reliability and minimising downtime are critical to both energy security and the financial viability of wind farms. Beyond energy balancing, uncertainty-aware forecasting also reduces operational uncertainty for wind farm operators, enabling more efficient maintenance scheduling and reducing costly unplanned downtime. This is especially important given that operation and maintenance costs represent a significant share of total expenditure, with unexpected failures making up the largest component [1, 2]. Supervisory control and data acquisition (SCADA) systems provide a low-cost and widely available source of wind turbine data. They capture environmental and operational variables with high frequency, making them invaluable for prediction applications. However, their use is complicated by measurement noise, turbine downtime, and limited public availability [3, 4].

The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces such as torque, joint angle, or end-effector position.

I am inclined to increase my score if the weaknesses are fixed