Bo Yang

MiniMax, Aili Chen, Aonian Li et al.

We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters activated per token. The M1 model natively supports a context length of 1 million tokens, 8x the context size of DeepSeek R1. Furthermore, the lightning attention mechanism in MiniMax-M1 enables efficient scaling of test-time compute. These properties make M1 particularly suitable for complex tasks that require processing long inputs and thinking extensively. MiniMax-M1 is trained using large-scale reinforcement learning (RL) on diverse problems including sandbox-based, real-world software engineering environments. In addition to M1's inherent efficiency advantage for RL training, we propose CISPO, a novel RL algorithm to further enhance RL efficiency. CISPO clips importance sampling weights rather than token updates, outperforming other competitive RL variants. Combining hybrid-attention and CISPO enables MiniMax-M1's full RL training on 512 H800 GPUs to complete in only three weeks, with a rental cost of just $534,700. We release two versions of MiniMax-M1 models with 40K and 80K thinking budgets respectively, where the 40K model represents an intermediate phase of the 80K training. Experiments on standard benchmarks show that our models are comparable or superior to strong open-weight models such as the original DeepSeek-R1 and Qwen3-235B, with particular strengths in complex software engineering, tool utilization, and long-context tasks. We publicly release MiniMax-M1 at https://github.com/MiniMax-AI/MiniMax-M1.

Jiaxu Cui, Bingyi Sun, Jiming Liu et al.

Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However, most existing methods only aim at learning network dynamic behaviors generated by a specific ordinary differential equation instance, resulting in ineffectiveness for new ones, and generally require dense observations. The observed data, especially from network emerging dynamics, are usually difficult to obtain, which brings trouble to model learning. Therefore, how to learn accurate network dynamics with sparse, irregularly-sampled, partial, and noisy observations remains a fundamental challenge. We introduce Neural ODE Processes for Network Dynamics (NDP4ND), a new class of stochastic processes governed by stochastic data-adaptive network dynamics, to overcome the challenge and learn continuous network dynamics from scarce observations. Intensive experiments conducted on various network dynamics in ecological population evolution, phototaxis movement, brain activity, epidemic spreading, and real-world empirical systems, demonstrate that the proposed method has excellent data adaptability and computational efficiency, and can adapt to unseen network emerging dynamics, producing accurate interpolation and extrapolation with reducing the ratio of required observation data to only about 6\% and improving the learning speed for new dynamics by three orders of magnitude.

Danli Shi, Bowen Liu, Zhen Tian et al.

Myopia, projected to affect 50% population globally by 2050, is a leading cause of vision loss. Eyes with pathological myopia exhibit distinctive shape distributions, which are closely linked to the progression of vision-threatening complications. Recent understanding of eye-shape-based biomarkers requires magnetic resonance imaging (MRI), however, it is costly and unrealistic in routine ophthalmology clinics. We present Fundus2Globe, the first AI framework that synthesizes patient-specific 3D eye globes from ubiquitous 2D color fundus photographs (CFPs) and routine metadata (axial length, spherical equivalent), bypassing MRI dependency. By integrating a 3D morphable eye model (encoding biomechanical shape priors) with a latent diffusion model, our approach achieves submillimeter accuracy in reconstructing posterior ocular anatomy efficiently. Fundus2Globe uniquely quantifies how vision-threatening lesions (e.g., staphylomas) in CFPs correlate with MRI-validated 3D shape abnormalities, enabling clinicians to simulate posterior segment changes in response to refractive shifts. External validation demonstrates its robust generation performance, ensuring fairness across underrepresented groups. By transforming 2D fundus imaging into 3D digital replicas of ocular structures, Fundus2Globe is a gateway for precision ophthalmology, laying the foundation for AI-driven, personalized myopia management.

Zeqi Leng, Chunxu Zhang, Guodong Long et al.

Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which represents the generalizable knowledge valuable to all participants in the Federated Learning (FL) system. To overcome this limitation, this paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters. This universal expert captures globally shared information across all clients and is subsequently distributed to each client as the initialization for the next round of model training. The proposed FL framework operates in three iterative steps: (1) local model training at each client, (2) cluster-specific model aggregation, and (3) universal expert distillation. This three-step learning paradigm ensures the preservation of fine-grained non-IID characteristics while effectively incorporating shared knowledge across clusters. Compared to traditional gradient-based aggregation methods, the distillation-based model aggregation introduces greater flexibility in handling model heterogeneity and reduces conflicts among cluster-specific experts. Extensive experimental results demonstrate the superior performance of the proposed method across various scenarios, highlighting its potential to advance the state of CFL by balancing personalized and shared knowledge more effectively.

Hongbin Pei, Bo Yang, Jiming Liu et al.

Predicting epidemic dynamics is of great value in understanding and controlling diffusion processes, such as infectious disease spread and information propagation. This task is intractable, especially when surveillance resources are very limited. To address the challenge, we study the problem of active surveillance, i.e., how to identify a small portion of system components as sentinels to effect monitoring, such that the epidemic dynamics of an entire system can be readily predicted from the partial data collected by such sentinels. We propose a novel measure, the gamma value, to identify the sentinels by modeling a sentinel network with row sparsity structure. We design a flexible group sparse Bayesian learning algorithm to mine the sentinel network suitable for handling both linear and non-linear dynamical systems by using the expectation maximization method and variational approximation. The efficacy of the proposed algorithm is theoretically analyzed and empirically validated using both synthetic and real-world data.