Understanding and constructing brain communications that capture dynamic communications across multiple regions is fundamental to modern system neuroscience, yet current methods struggle to find time-varying region-level communications or scale to large neural datasets with long recording durations. We present a novel framework using Markovian Gaussian Processes to learn brain communications with time-varying temporal delays from multi-region neural recordings, named Adaptive Delay Model (ADM). Our method combines Gaussian Processes with State Space Models and employs parallel scan inference algorithms, enabling efficient scaling to large datasets while identifying concurrent communication patterns that evolve over time. This time-varying approach captures how brain region interactions shift dynamically during cognitive processes. Validated on synthetic and multi-region neural recordings datasets, our approach discovers both the directionality and temporal dynamics of neural communication. This work advances our understanding of distributed neural computation and provides a scalable tool for analyzing dynamic brain networks.

Studying the complex interactions between different brain regions is crucial in neuroscience. Various statistical methods have explored the latent communication across multiple brain regions. Two main categories are the Gaussian Process (GP) and Linear Dynamical System (LDS), each with unique strengths. The GP-based approach effectively discovers latent variables with frequency bands and communication directions. Conversely, the LDS-based approach is computationally efficient but lacks powerful expressiveness in latent representation. In this study, we merge both methodologies by creating an LDS mirroring a multi-output GP, termed Multi-Region Markovian Gaussian Process (MRM-GP). Our work establishes a connection between an LDS and a multi-output GP that explicitly models frequencies and phase delays within the latent space of neural recordings. Consequently, the model achieves a linear inference cost over time points and provides an interpretable low-dimensional representation, revealing communication directions across brain regions and separating oscillatory communications into different frequency bands.

The partially observable generalized linear model (POGLM) is a powerful tool for understanding neural connectivities under the assumption of existing hidden neurons. With spike trains only recorded from visible neurons, existing works use variational inference to learn POGLM meanwhile presenting the difficulty of learning this latent variable model. There are two main issues: (1) the sampled Poisson hidden spike count hinders the use of the pathwise gradient estimator in VI; and (2) the existing design of the variational model is neither expressive nor time-efficient, which further affects the performance. For (1), we propose a new differentiable POGLM, which enables the pathwise gradient estimator, better than the score function gradient estimator used in existing works. For (2), we propose the forward-backward message-passing sampling scheme for the variational model. Comprehensive experiments show that our differentiable POGLMs with our forward-backward message passing produce a better performance on one synthetic and two real-world datasets. Furthermore, our new method yields more interpretable parameters, underscoring its significance in neuroscience.

Understanding the neural basis of behavior is a fundamental goal in neuroscience. Current research in large-scale neuro-behavioral data analysis often relies on decoding models, which quantify behavioral information in neural data but lack details on behavior encoding. This raises an intriguing scientific question: "how can we enable in-depth exploration of neural representations in behavioral tasks, revealing interpretable neural dynamics associated with behaviors". However, addressing this issue is challenging due to the varied behavioral encoding across different brain regions and mixed selectivity at the population level. To tackle this limitation, our approach, named ("BeNeDiff"), first identifies a fine-grained and disentangled neural subspace using a behavior-informed latent variable model. It then employs state-of-the-art generative diffusion models to synthesize behavior videos that interpret the neural dynamics of each latent factor. We validate the method on multi-session datasets containing widefield calcium imaging recordings across the dorsal cortex. Through guiding the diffusion model to activate individual latent factors, we verify that the neural dynamics of latent factors in the disentangled neural subspace provide interpretable quantifications of the behaviors of interest. At the same time, the neural subspace in BeNeDiff demonstrates high disentanglement and neural reconstruction quality.

The popularity of Deepfake technology has raised the challenge of recognizing real and fake faces. While detection methods already exist, most of them are passive forensics and face challenges of generalizability and migration. Currently, some research attempts to protect the original image by priorly inserting invisible information. However, there are still shortcomings in terms of image quality and information robustness due to information embedding, i.e., watermarking. Therefore, we employ the robustness of perceptual hash coding and combine it with information hiding techniques to propose a proactive Deepfake detection solution, referred to as PWPH in this paper. Our approach is simple and efficient: first, the image containing a face is divided into two parts: FA (face area), and NFA (non-face area). A perceptual hash code is generated from the non-face area (NFA). Then, the hash codes are embedded as watermarks into the FA. At the extraction stage, we use the same method as the encoder to retrieve the embedded watermark from FA. The watermark is then compared with the hash code generated from the NFA of the detected image. The extracted watermark is sensitive to distortion and may vanish during Deepfake processing. Experimental results validate that our method, requiring just one encoder and decoder, enables active detection and source tracking. Furthermore, its efficacy in typical Deepfake scenarios such as face swapping and expression reconstruction is confirmed through comparison with prior arts.

In collaborative filtering, it is an important way to make full use of social information to improve the recommendation quality, which has been proved to be effective because user behavior will be affected by her friends. However, existing works leverage the social relationship to aggregate user features from friends' historical behavior sequences in a user-levelindirect paradigm. A significant defect of the indirect paradigm is that it ignores the temporal relationships between behavior events across users. In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user's dynamic interests in an event-leveldirect paradigm. Moreover, we propose to decompose the temporal effect in sequential recommendation into social mutual temporal effect and ego temporal effect. Specifically, we employ a social heterogeneous graph embedding layer to refine user representation via structural information. To enhance temporal information propagation, STEN directly extracts the fine-grained temporal mutual influence of friends' behaviors through themutually exciting temporal network. Besides, user's dynamic interests are captured through theself-exciting temporal network. Extensive experiments on three real-world datasets show that STEN outperforms state-of-the-art baseline methods. Moreover, STEN provides event-level recommendation explainability, which is also illustrated experimentally.

The log-ratio (LR) operator has been widely employed to generate the difference image for synthetic aperture radar (SAR) image change detection. However, the difference image generated by this pixelwise operator can be subject to SAR images speckle and unavoidable registration errors between bitemporal SAR images. In this letter, we proposed a spatial metric learning method to obtain a difference image that is more robust to the speckle by learning a metric from a set of constraint pairs. In the proposed method, the spatial context is considered in constructing constraint pairs, each of which consists of patches in the same location of bitemporal SAR images. Then, a semidefinite positive metric matrix M can be obtained by the optimization with the max-margin criterion. Finally, we verify our proposed method on four challenging data sets of bitemporal SAR images. Experimental results demonstrate that the difference map obtained by our proposed method outperforms than other state-of-the-art methods.