To advance time series forecasting (TSF), various methods have been proposed to improve prediction accuracy, evolving from statistical techniques to data-driven deep learning architectures. Despite their effectiveness, most existing methods still adhere to a fast thinking paradigm-relying on extracting historical patterns and mapping them to future values as their core modeling philosophy, lacking an explicit thinking process that incorporates intermediate time series reasoning. Meanwhile, emerging slow-thinking LLMs (e.g., OpenAI-o1) have shown remarkable multi-step reasoning capabilities, offering an alternative way to overcome these issues. However, prompt engineering alone presents several limitations - including high computational cost, privacy risks, and limited capacity for in-depth domain-specific time series reasoning. To address these limitations, a more promising approach is to train LLMs to develop slow thinking capabilities and acquire strong time series reasoning skills. For this purpose, we propose Time-R1, a two-stage reinforcement fine-tuning framework designed to enhance multi-step reasoning ability of LLMs for time series forecasting. Specifically, the first stage conducts supervised fine-tuning for warmup adaptation, while the second stage employs reinforcement learning to improve the model's generalization ability. Particularly, we design a fine-grained multi-objective reward specifically for time series forecasting, and then introduce GRIP (group-based relative importance for policy optimization), which leverages non-uniform sampling to further encourage and optimize the model's exploration of effective reasoning paths. Experiments demonstrate that Time-R1 significantly improves forecast performance across diverse datasets.

Density regression models allow a comprehensive understanding of data by modeling the complete conditional probability distribution. While flexible estimation approaches such as normalizing flows (NF) work particularly well in multiple dimensions, interpreting the input-output relationship of such models is often difficult, due to the black-box character of deep learning models. In contrast, existing statistical methods for multivariate outcomes such as multivariate conditional transformation models (MCTM) are restricted in flexibility and are often not expressive enough to represent complex multivariate probability distributions. In this paper, we combine MCTM with state-of-the-art and autoregressive NF to leverage the transparency of MCTM for modeling interpretable feature effects on the marginal distributions in the first step and the flexibility of neural-network-based NF techniques to account for complex and non-linear relationships in the joint data distribution. We demonstrate our method's versatility in various numerical experiments and compare it with MCTM and other NF models on both simulated and real-world data.

Machine learning algorithms often struggle to control complex real-world systems. In the case of nuclear fusion, these challenges are exacerbated, as the dynamics are notoriously complex, data is poor, hardware is subject to failures, and experiments often affect dynamics beyond the experiment's duration. Existing tools like reinforcement learning, supervised learning, and Bayesian optimization address some of these challenges but fail to provide a comprehensive solution. To overcome these limitations, we present a multi-scale Bayesian optimization approach that integrates a high-frequency data-driven dynamics model with a low-frequency Gaussian process. By updating the Gaussian process between experiments, the method rapidly adapts to new data, refining the predictions of the less reliable dynamical model. We validate our approach by controlling tearing instabilities in the DIII-D nuclear fusion plant. Offline testing on historical data shows that our method significantly outperforms several baselines. Results on live experiments on the DIII-D tokamak, conducted under high-performance plasma scenarios prone to instabilities, shows a 50% success rate, marking a 117% improvement over historical outcomes.

Control tasks with safety requirements under high levels of model uncertainty are increasingly common. Machine learning techniques are frequently used to address such tasks, typically by leveraging model error bounds to specify robust constraint-based safety filters. However, if the learned model uncertainty is very high, the corresponding filters are potentially invalid, meaning no control input satisfies the constraints imposed by the safety filter. While most works address this issue by assuming some form of safe backup controller, ours tackles it by collecting additional data on the fly using a Gaussian process bandit-type algorithm. We combine a control barrier function with a learned model to specify a robust certificate that ensures safety if feasible. Whenever infeasibility occurs, we leverage the control barrier function to guide exploration, ensuring the collected data contributes toward the closed-loop system safety. By combining a safety filter with exploration in this manner, our method provably achieves safety in a setting that allows for a zero-mean prior dynamics model, without requiring a backup controller. To the best of our knowledge, it is the first safe learning-based control method that achieves this.

In robot navigation and manipulation, accurately determining the camera's pose relative to the environment is crucial for effective task execution. In this paper, we systematically prove that this problem corresponds to the Perspective-3-Point (P3P) formulation, where exactly three known 3D points and their corresponding 2D image projections are used to estimate the pose of a stereo camera. In image-based visual servoing (IBVS) control, the system becomes overdetermined, as the 6 degrees of freedom (DoF) of the stereo camera must align with 9 observed 2D features in the scene. When more constraints are imposed than available DoFs, global stability cannot be guaranteed, as the camera may become trapped in a local minimum far from the desired configuration during servoing. To address this issue, we propose a novel control strategy for accurately positioning a calibrated stereo camera. Our approach integrates a feedforward controller with a Youla parameterization-based feedback controller, ensuring robust servoing performance. Through simulations, we demonstrate that our method effectively avoids local minima and enables the camera to reach the desired pose accurately and efficiently.

We introduce~\textsc{Domain2Vec}, a novel approach that decomposes any dataset into a linear combination of several \emph{meta-domains}, a new concept designed to capture the key underlying features of datasets. \textsc{Domain2Vec} maintains a vocabulary of meta-domains and uses a classifier to decompose any given dataset into a domain vector that corresponds to a distribution over this vocabulary. These domain vectors enable the identification of the optimal data mixture for language model (LM) pretraining in a training-free manner under the \emph{\textbf{D}istribution \textbf{A}lignment \textbf{A}ssumption} (DA$^{2}$), which suggests that when the data distributions of the training set and the validation set are better aligned, a lower validation loss is achieved. Moreover, \textsc{Domain2vec} can be seamlessly integrated into previous works to model the relationship between domain vectors and LM performance, greatly enhancing the efficiency and scalability of previous methods. Extensive experiments demonstrate that \textsc{Domain2Vec} helps find the data mixture that enhances downstream task performance with minimal computational overhead. Specifically, \textsc{Domain2Vec} achieves the same validation loss on Pile-CC using only $51.5\%$ of the computation required when training on the original mixture of The Pile dataset. Under equivalent compute budget, \textsc{Domain2Vec} improves downstream performance by an average of $2.83\%$.

Understanding and controlling the atomistic-level reactions governing the formation of the solid-electrolyte interphase (SEI) is crucial for the viability of next-generation solid state batteries. However, challenges persist due to difficulties in experimentally characterizing buried interfaces and limits in simulation speed and accuracy. We conduct large-scale explicit reactive simulations with quantum accuracy for a symmetric battery cell, {\symcell}, enabled by active learning and deep equivariant neural network interatomic potentials. To automatically characterize the coupled reactions and interdiffusion at the interface, we formulate and use unsupervised classification techniques based on clustering in the space of local atomic environments. Our analysis reveals the formation of a previously unreported crystalline disordered phase, Li$_2$S$_{0.72}$P$_{0.14}$Cl$_{0.14}$, in the SEI, that evaded previous predictions based purely on thermodynamics, underscoring the importance of explicit modeling of full reaction and transport kinetics. Our simulations agree with and explain experimental observations of the SEI formations and elucidate the Li creep mechanisms, critical to dendrite initiation, characterized by significant Li motion along the interface. Our approach is to crease a digital twin from first principles, without adjustable parameters fitted to experiment. As such, it offers capabilities to gain insights into atomistic dynamics governing complex heterogeneous processes in solid-state synthesis and electrochemistry.

We propose a novel energy function for Dense Associative Memory (DenseAM) networks, the log-sum-ReLU (LSR), inspired by optimal kernel density estimation. Unlike the common log-sum-exponential (LSE) function, LSR is based on the Epanechnikov kernel and enables exact memory retrieval with exponential capacity without requiring exponential separation functions. Moreover, it introduces abundant additional \emph{emergent} local minima while preserving perfect pattern recovery -- a characteristic previously unseen in DenseAM literature. Empirical results show that LSR energy has significantly more local minima (memories) that have comparable log-likelihood to LSE-based models. Analysis of LSR's emergent memories on image datasets reveals a degree of creativity and novelty, hinting at this method's potential for both large-scale memory storage and generative tasks.

The Reference Remote Sensing Image Segmentation (RRSIS) task generates segmentation masks for specified objects in images based on textual descriptions, which has attracted widespread attention and research interest. Current RRSIS methods rely on multi-modal fusion backbones and semantic segmentation heads but face challenges like dense annotation requirements and complex scene interpretation. To address these issues, we propose a framework named \textit{prompt-generated semantic localization guiding Segment Anything Model}(PSLG-SAM), which decomposes the RRSIS task into two stages: coarse localization and fine segmentation. In coarse localization stage, a visual grounding network roughly locates the text-described object. In fine segmentation stage, the coordinates from the first stage guide the Segment Anything Model (SAM), enhanced by a clustering-based foreground point generator and a mask boundary iterative optimization strategy for precise segmentation. Notably, the second stage can be train-free, significantly reducing the annotation data burden for the RRSIS task. Additionally, decomposing the RRSIS task into two stages allows for focusing on specific region segmentation, avoiding interference from complex scenes.We further contribute a high-quality, multi-category manually annotated dataset. Experimental validation on two datasets (RRSIS-D and RRSIS-M) demonstrates that PSLG-SAM achieves significant performance improvements and surpasses existing state-of-the-art models.Our code will be made publicly available.

The site of the secret Manhattan Project in Oak Ridge, Tennessee has a new mission to help achieve an A.I. advantage over China. A new uranium enrichment facility in Oak Ridge will supply nuclear fuel to the reactors that power A.I. data centers. Over 80 years after scientists of the'Manhattan Project' harnessed the power of the atom to end World War II, the top-secret worksite has a new mission to help dominate AI before China does. The first phase of the United States' latest uranium enrichment facility opened in Oak Ridge, Tennessee in May. Uranium powers the nuclear reactors the AI data centers are turning to for reliable energy.