Z. Huang

MiroMind Team, S. Bai, L. Bing et al.

We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage that emphasizes structured planning, contextual reasoning, and tool interaction. This enables more effective multi-step interaction and sustained reasoning across complex tasks. MiroThinker-H1 further incorporates verification directly into the reasoning process at both local and global levels. Intermediate reasoning decisions can be evaluated and refined during inference, while the overall reasoning trajectory is audited to ensure that final answers are supported by coherent chains of evidence. Across benchmarks covering open-web research, scientific reasoning, and financial analysis, MiroThinker-H1 achieves state-of-the-art performance on deep research tasks while maintaining strong results on specialized domains. We also release MiroThinker-1.7 and MiroThinker-1.7-mini as open-source models, providing competitive research-agent capabilities with significantly improved efficiency.

W. He, Z. Huang, X. Meng et al.

In the era of pre-trained models, image clustering task is usually addressed by two relevant stages: a) to produce features from pre-trained vision models; and b) to find clusters from the pre-trained features. However, these two stages are often considered separately or learned by different paradigms, leading to suboptimal clustering performance. In this paper, we propose a unified framework, termed graph Cut-guided Maximal Coding Rate Reduction (CgMCR$^2$), for jointly learning the structured embeddings and the clustering. To be specific, we attempt to integrate an efficient clustering module into the principled framework for learning structured representation, in which the clustering module is used to provide partition information to guide the cluster-wise compression and the learned embeddings is aligned to desired geometric structures in turn to help for yielding more accurate partitions. We conduct extensive experiments on both standard and out-of-domain image datasets and experimental results validate the effectiveness of our approach.

A. Hanuka, C. Emma, T. Maxwell et al.

Longitudinal phase space (LPS) provides a critical information about electron beam dynamics for various scientific applications. For example, it can give insight into the high-brightness X-ray radiation from a free electron laser. Existing diagnostics are invasive, and often times cannot operate at the required resolution. In this work we present a machine learning-based Virtual Diagnostic (VD) tool to accurately predict the LPS for every shot using spectral information collected non-destructively from the radiation of relativistic electron beam. We demonstrate the tool's accuracy for three different case studies with experimental or simulated data. For each case, we introduce a method to increase the confidence in the VD tool. We anticipate that spectral VD would improve the setup and understanding of experimental configurations at DOE's user facilities as well as data sorting and analysis. The spectral VD can provide confident knowledge of the longitudinal bunch properties at the next generation of high-repetition rate linear accelerators while reducing the load on data storage, readout and streaming requirements.

Enrico Camporeale, M. D. Cash, H. J. Singer et al.

We present a novel algorithm that predicts the probability that the time derivative of the horizontal component of the ground magnetic field $dB/dt$ exceeds a specified threshold at a given location. This quantity provides important information that is physically relevant to Geomagnetically Induced Currents (GIC), which are electric currents { associated to} sudden changes in the Earth's magnetic field due to Space Weather events. The model follows a 'gray-box' approach by combining the output of a physics-based model with machine learning. Specifically, we combine the University of Michigan's Geospace model that is operational at the NOAA Space Weather Prediction Center, with a boosted ensemble of classification trees. We discuss the problem of re-calibrating the output of the decision tree to obtain reliable probabilities. The performance of the model is assessed by typical metrics for probabilistic forecasts: Probability of Detection and False Detection, True Skill Statistic, Heidke Skill Score, and Receiver Operating Characteristic curve. We show that the ML enhanced algorithm consistently improves all the metrics considered.