Core Viewpoint - The article discusses the limitations of current spatial transcriptomics (ST) technologies, which primarily operate in two dimensions, and introduces a new computational framework called SpatialZ that enables the reconstruction of dense 3D cell atlases from sparse 2D slices, significantly enhancing the understanding of biological functions and tissue organization [2][3][10]. Group 1: Limitations of Current Technologies - Current ST technologies are limited to 2D observations, making it difficult to capture the continuous gradients of gene expression and the intricate cellular interactions within organs [2]. - The compromise in sampling density along the Z-axis due to high experimental costs leads to significant gaps in data, resulting in a fragmented view of biological tissues [2]. Group 2: Introduction of SpatialZ - SpatialZ is a novel computational framework that integrates optimal transport theory to generate virtual slices between sparse real slices, facilitating the transition from discrete 2D data to dense 3D maps [3][5]. - The framework has successfully constructed a digital mouse brain atlas containing over 38 million cell gene expressions and 3D coordinates, marking a significant advancement in the field of life sciences [3][8]. Group 3: Methodology of SpatialZ - SpatialZ employs a four-step algorithm for high-fidelity 3D reconstruction, including spatial alignment, position generation, cell state inference, and expression profile inference [5]. - The methodology ensures that the generated cells not only have accurate spatial positioning but also reflect the biological states and microenvironment characteristics [5]. Group 4: Validation and Performance - The reliability of SpatialZ was validated using mouse visual cortex data, showing that it accurately restored missing intermediate layer information and maintained high consistency with ground truth data [6][7]. - The framework demonstrated improved correlation and statistical significance compared to unprocessed sparse sampling data, effectively addressing structural information gaps caused by sparse sampling [7]. Group 5: Broader Applications - SpatialZ's underlying logic is highly generalizable, allowing its application in spatial proteomics, spatial metabolomics, and other multi-omics data, providing new perspectives for complex disease research [9]. - The framework has been successfully applied to human breast cancer tissue imaging mass cytometry data, correcting expression anomalies caused by tissue loss or technical artifacts, thus aiding in spatial screening for tumor immunotherapy targets [9]. Group 6: Conclusion - SpatialZ represents a breakthrough in computational methods, bridging the gap from single-cell analysis to organ-level digitalization, and offers a standardized digital reference for neuroscience research [10]. - The framework opens new possibilities for constructing comprehensive 3D spatial maps across modalities, organs, and species, potentially leading to new discoveries in developmental biology, neuroscience, and oncology [10].

Core Viewpoint - The article discusses the comprehensive guide on diffusion models, highlighting their transformative impact on generative AI across various domains such as images, audio, video, and 3D environments [2][4]. Summary by Sections Introduction to Diffusion Models - Diffusion models are presented as a method that views the generation process as a gradual transformation over time, contrasting with traditional generative models that directly learn mappings from noise to data [11]. - The article emphasizes the need for a systematic understanding of diffusion models, which the book aims to provide, making it a valuable resource for both researchers and beginners [6][9]. Core Principles of Diffusion Models - The book outlines the foundational principles of diffusion models, connecting three key perspectives: variational methods, score-based methods, and flow-based methods, which together form a unified theoretical framework [11][13]. - It discusses how these models achieve efficient sample generation and enhanced controllability during the generation process [12]. Detailed Exploration of Perspectives - The variational view relates to denoising diffusion probabilistic models (DDPMs), providing a basis for probabilistic inference and optimization [23]. - The score-based view focuses on learning score functions to guide the denoising process, linking diffusion modeling with classical differential equation theory [23][24]. - The flow-based view describes the generation process as a continuous flow transformation, allowing for broader applications beyond simple generation tasks [24]. Sampling Techniques and Efficiency - The article highlights the unique feature of diffusion models, which refine samples from coarse to fine through noise removal, and discusses the trade-off between performance and efficiency [27][28]. - It introduces methods for improving sampling performance without retraining models, such as classifier guidance and advanced numerical solvers to enhance generation quality and speed [29][30]. Learning Fast Generative Models - The book explores strategies for directly learning fast generative models that approximate the diffusion process, aiming to reduce reliance on multi-step inference [30][31]. - Distillation-based methods are discussed, where a student model mimics a slower teacher model to achieve faster sampling while maintaining quality [30]. Comprehensive Coverage of Diffusion Models - The book aims to establish a lasting theoretical framework for diffusion models, focusing on continuous time dynamical systems that connect simple prior distributions to data distributions [33]. - It emphasizes the importance of understanding the underlying principles and connections between different methods to design and improve next-generation generative models [36].

Core Viewpoint - The article discusses the hidden dangers of the DeepSeek-R1 model, which, despite its strong reasoning capabilities, may leak harmful content during its thought process even when it refuses to answer questions. Existing defense technologies face a dilemma: they either fail to prevent attacks or overly restrict the model's responses, leading to a situation where normal questions are also rejected [1][2]. Summary by Sections Section 1: Introduction of X-Boundary - Shanghai Jiao Tong University and Shanghai AI Lab have jointly developed a security defense solution called X-Boundary, aiming to resolve the dilemma of existing defense technologies by separating harmful representations and eliminating them without compromising the model's general performance [2][3]. Section 2: Performance Analysis - X-Boundary has shown significant improvements in the DeepSeek-R1-Distill-Llama-8B model, effectively blocking information leakage by removing harmful features, akin to implanting a "cognitive purification chip" [3][4]. Section 3: Defense Methods and Challenges - The article highlights a critical imbalance between safety and intelligence in mainstream defense methods (SFT/DPO/GA/CB). While these methods reduce the attack success rate (ASR), they also significantly impair the model's reasoning capabilities, with a reported 10% drop in mathematical ability and over 50% of safety questions being unjustly rejected [5][6]. Section 4: Multi-Round Defense Training - Introducing multi-round defense data into models like Qwen2.5-7B-Chat has led to a 30% increase in misclassification rates, indicating a strong correlation between increased defense strength and usability loss. The existing methods struggle to clearly distinguish between harmful and benign queries, leading to excessive safety measures [6][7]. Section 5: X-Boundary Framework - The X-Boundary defense framework aims to create an "internal safety system" for large models, allowing for precise interception of dangerous content while ensuring safe information can pass through without detection [7][8]. Section 6: Dynamic Protection Network - The framework consists of three steps: 1. Boundary Drawing: Optimizing representation separation to prevent confusion between harmful and safe requests [8]. 2. Threat Dissolution: Applying irreversible perturbations to harmful representations [8]. 3. Intelligent Preservation: Maintaining the integrity of safe representations during training [8]. Section 7: Theoretical and Practical Validation - X-Boundary is supported by optimal transport theory, which enhances the clustering of safe representations, leading to faster convergence during model training. Experiments show a 27% and 18% improvement in convergence speed for Llama-3-8B and Qwen2.5-7B models, respectively [9][10]. Section 8: Balancing Safety and Intelligence - X-Boundary successfully establishes a clear boundary between harmful and safe representations within the model, addressing the chaos of traditional methods that fail to differentiate between the two [10][11]. Section 9: Robust Multi-Round Defense - With a clear distinction in representations, X-Boundary achieves a balance between safety and usability, maintaining over 99% of the model's original performance while minimizing misclassification rates [13][14]. Section 10: Scalability - When applied to larger models, such as the 14 billion parameter Qwen2.5-14B-Chat, X-Boundary continues to provide effective zero-perception defense, demonstrating its robustness across different model scales [15].