Xinyue Zhao

Xuehai Huang, Xinyue Zhao

A symmetric-tensor distributional mixed method for a fourth-order elliptic singular perturbation problem is developed in this paper. The moment variable is approximated by normal-normal continuous symmetric tensor elements, while the scalar variable is represented by an $H^1$-nonconforming virtual element space coupled with a polynomial multiplier on interior subsimplices of codimension two. Optimal parameter-uniform error estimates are derived, independent of the presence of boundary layers. A hybridized form of the method is also equivalent to stabilization-free weak Galerkin and $H^2$-nonconforming virtual element methods. In two dimensions, a close connection of the distributional mixed method to the classical Hellan-Herrmann-Johnson (HHJ) method is established, by naturally identifying the scalar virtual element-multiplier pair with the Lagrange finite element space. Thus the proposed method extends the two-dimensional HHJ method to arbitrary spatial dimensions. Three-dimensional numerical experiments support the theoretical convergence and robustness estimates.

Meituan LongCat Team, Anchun Gui, Bei Li et al.

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain-of-Thought (CoT) data cold-start and culminating in large-scale Reinforcement Learning (RL). We first employ a well-designed cold-start training strategy, which significantly enhances the reasoning potential and equips the model with specialized skills in both formal and agentic reasoning. Then, a core innovation is our domain-parallel training scheme, which decouples optimization across distinct domains (e.g., STEM, Code, Agentic) and subsequently fuses the resulting expert models into a single, nearly Pareto-optimal model. This entire process is powered by our Dynamic ORchestration for Asynchronous rollout (DORA) system, a large-scale RL framework that delivers a greater than threefold training speedup over synchronous methods on tens of thousands of accelerators. As a result, LongCat-Flash-Thinking achieves state-of-the-art performance among open-source models on a suite of complex reasoning tasks. The model exhibits exceptional efficiency in agentic reasoning, reducing average token consumption by 64.5% (from 19, 653 to 6, 965) on AIME-25, without degrading task accuracy. We release LongCat-Flash-Thinking to promote further advances in reasoning systems and agentic AI research.

Chentao Shen, Ding Pan, Mingyu Mei et al.

Visual pose tracking is playing an increasingly vital role in industrial contexts in recent years. However, the pose tracking for industrial metal objects remains a challenging task especially in the real world-environments, due to the reflection characteristic of metal objects. To address this issue, we propose a novel 6DoF pose tracking method based on active control points. The method uses image control points to generate edge feature for optimization actively instead of 6DoF pose-based rendering, and serve them as optimization variables. We also introduce an optimal control point regression method to improve robustness. The proposed tracking method performs effectively in both dataset evaluation and real world tasks, providing a viable solution for real-time tracking of industrial metal objects. Our source code is made publicly available at: https://github.com/tomatoma00/ACPTracking.

Long Chen, Xuehai Huang, Chao Zhang et al.

This paper develops divergence-free mixed finite element methods for the Stokes equation. Using H(div)-conforming velocities and discontinuous pressures ensures the inf-sup condition for the velocity--pressure pair and yields pointwise divergence-free velocities. However, this choice makes the vector Laplacian difficult to discretize. Inspired by mass-conserving mixed formulations with stresses, tangential--normal continuous traceless tensor elements are introduced to discretize the vector Laplacian. An inf-sup condition for the weak div operator between the stress and velocity spaces is then proved. Two key properties characterize the scheme. First, the stress--velocity inf-sup stability gives a stable discretization of the vector Laplacian without additional stabilization, unlike discontinuous Galerkin or virtual element methods. Second, the scheme has the property that if a stress field is weakly divergence-free, then it is also strongly divergence-free. This decouples the stress and velocity errors and leads to superconvergence. As a result, optimal-order error estimates are obtained for the stress, while the velocity and pressure converge at rates higher than the approximation orders of the chosen spaces. Numerical experiments confirm the theoretical results.