Large-scale EEG foundation models have shown strong generalization across a range of downstream tasks, but their training remains resource-intensive due to the volume and variable quality of EEG data. In this work, we introduce EEG-DLite, a data distillation framework that enables more efficient pre-training by selectively removing noisy and redundant samples from large EEG datasets. EEG-DLite begins by encoding EEG segments into compact latent representations using a self-supervised autoencoder, allowing sample selection to be performed efficiently and with reduced sensitivity to noise. Based on these representations, EEG-DLite filters out outliers and minimizes redundancy, resulting in a smaller yet informative subset that retains the diversity essential for effective foundation model training. Through extensive experiments, we demonstrate that training on only 5 percent of a 2,500-hour dataset curated with EEG-DLite yields performance comparable to, and in some cases better than, training on the full dataset across multiple downstream tasks. To our knowledge, this is the first systematic study of pre-training data distillation in the context of EEG foundation models. EEG-DLite provides a scalable and practical path toward more effective and efficient physiological foundation modeling.

The non-stationary nature of electroencephalography (EEG) introduces distribution shifts across domains (e.g., days and subjects), posing a significant challenge to EEG-based neurotechnology generalization. Without labeled calibration data for target domains, the problem is a source-free unsupervised domain adaptation (SFUDA) problem. For scenarios with constant label distribution, Riemannian geometry-aware statistical alignment frameworks on the symmetric positive definite (SPD) manifold are considered state-of-the-art. However, many practical scenarios, including EEG-based sleep staging, exhibit label shifts. Here, we propose a geometric deep learning framework for SFUDA problems under specific distribution shifts, including label shifts. We introduce a novel, realistic generative model and show that prior Riemannian statistical alignment methods on the SPD manifold can compensate for specific marginal and conditional distribution shifts but hurt generalization under label shifts. As a remedy, we propose a parameter-efficient manifold optimization strategy termed SPDIM. SPDIM uses the information maximization principle to learn a single SPD-manifold-constrained parameter per target domain. In simulations, we demonstrate that SPDIM can compensate for the shifts under our generative model. Moreover, using public EEG-based brain-computer interface and sleep staging datasets, we show that SPDIM outperforms prior approaches.

Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation. These methods enable the synthesis of detailed and photorealistic textured objects. However, the appearance of 3D objects produced by such text-to-3D models is often unpredictable, and it is hard for single-image-to-3D methods to deal with images lacking a clear subject, complicating the generation of appearance-controllable 3D objects from complex images. To address these challenges, we present IPDreamer, a novel method that captures intricate appearance features from complex **I**mage **P**rompts and aligns the synthesized 3D object with these extracted features, enabling high-fidelity, appearance-controllable 3D object generation. Our experiments demonstrate that IPDreamer consistently generates high-quality 3D objects that align with both the textual and complex image prompts, highlighting its promising capability in appearance-controlled, complex 3D object generation.

The card game Dou Di Zhu (competitive two-against-one game) presents a challenging multiplayer imperfect-information game problem due to its large action space. We developed a deep Monte Carlo (DMC) reinforcement learning (RL) framework called ASP-DouZero, which employs dynamic programming (DP) to prune the action space effectively, using statistical analysis results. The pruned action space was then applied to self-play data generation and neural network decision processes. We evaluated ASP-DouZero against the state-of-the-art DouZero framework under identical training conditions. Results showed the proposed approach achieved a 5% higher win rate in standardized matches after convergence while requiring 50% less training time on equivalent hardware. These findings demonstrate that action space pruning significantly improves decision-making performance and training efficiency in DMC-based approaches for Dou Di Zhu.

Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data. Existing FL methods either iteratively share local model parameters or deploy co-distillation. However, the former is highly susceptible to private data leakage, and the latter design relies on the prerequisites of task-relevant real data. Instead, we propose a data-free FL framework based on local-to-central collaborative distillation with direct input and output space exploitation. Our design eliminates any requirement of recursive local parameter exchange or auxiliary task-relevant data to transfer knowledge, thereby giving direct privacy control to local users. In particular, to cope with the inherent data heterogeneity across locals, our technique learns to distill input on which each local model produces consensual yet unique results to represent each expertise. Our proposed FL framework achieves notable privacy-utility trade-offs with extensive experiments on image classification and segmentation tasks under various real-world heterogeneous federated learning settings on both natural and medical images. Code is available at https://github.com/lsl001006/FedIOD.

Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models. Diffusion-based methods have recently shown promise in analyzing functional magnetic resonance imaging (fMRI) data, including the reconstruction of high-quality images consistent with original visual stimuli. Nonetheless, it remains a critical challenge to effectively harness the semantic and silhouette information extracted from brain signals. In this paper, we propose a novel approach, termed as Controllable Mind Visual Diffusion Model (CMVDM). Specifically, CMVDM first extracts semantic and silhouette information from fMRI data using attribute alignment and assistant networks. Then, a control model is introduced in conjunction with a residual block to fully exploit the extracted information for image synthesis, generating high-quality images that closely resemble the original visual stimuli in both semantic content and silhouette characteristics. Through extensive experimentation, we demonstrate that CMVDM outperforms existing state-of-the-art methods both qualitatively and quantitatively. Our code is available at https://github.com/zengbohan0217/CMVDM.

3D face reconstruction aims at generating high-fidelity 3D face shapes and textures from single-view or multi-view images. However, current prevailing facial texture generation methods generally suffer from low-quality texture, identity information loss, and inadequate handling of occlusions. To solve these problems, we introduce an Identity-Conditioned Latent Diffusion Model for face UV-texture generation (UV-IDM) to generate photo-realistic textures based on the Basel Face Model (BFM). UV-IDM leverages the powerful texture generation capacity of a latent diffusion model (LDM) to obtain detailed facial textures. To preserve the identity during the reconstruction procedure, we design an identity-conditioned module that can utilize any in-the-wild image as a robust condition for the LDM to guide texture generation. UV-IDM can be easily adapted to different BFM-based methods as a high-fidelity texture generator. Furthermore, in light of the limited accessibility of most existing UV-texture datasets, we build a large-scale and publicly available UV-texture dataset based on BFM, termed BFM-UV. Extensive experiments show that our UV-IDM can generate high-fidelity textures in 3D face reconstruction within seconds while maintaining image consistency, bringing new state-of-the-art performance in facial texture generation.

Recent advances in vision-language models like Stable Diffusion have shown remarkable power in creative image synthesis and editing. However, most existing text-to-image editing methods encounter two obstacles: First, the text prompt needs to be carefully crafted to achieve good results, which is not intuitive or user-friendly. Second, they are in-sensitive to local edits and can irreversibly affect non-edited regions, leaving obvious editing traces. To tackle these problems, we propose a Zero-shot instructiON-guided local image Editing approach, termed ZONE. We first convert the editing intent from the user-provided instruction (e.g., “make his tie blue”) into specific image editing regions through InstructPix2Pix. We then propose a Region-loll scheme for precise image layer extraction from an off-the-shelf segment model. We further develop an edge smoother based on FFT for seamless blending between the layer and the image. Our method allows for arbitrary manipulation of a specific region with a single instruction while preserving the rest. Extensive experiments demonstrate that our Z ONE achieves remarkable local editing results and user-friendliness, outperforming state-of-the-art methods. Code is available at https://github.com/ls1001006/ZONE.

Electroencephalography (EEG) based brain-computer interfaces (BCIs) face great challenges in generalizing across different domains (i.e., sessions and subjects) without costly supervised calibration.To avoid supervised calibration, transfer learning, particularly unsupervised domain adaptation, has been a popular approach.In this work, we focus on a geometric deep learning framework previously proposed for EEG-based mental imagery BCIs.The framework aligns marginal feature distributions in latent space, assuming identical label distributions across domains.Here, we propose a novel approach integrating data augmentation and clustering techniques to align the latent distributions under label shifts.

This article investigates the problem of finite-frequency fault estimation (FE) and adaptive event-triggered fault-tolerant consensus for linear parameter-varying multiagent systems. A polytopic parameter-varying framework is introduced to represent the dynamics of each agent with internal model perturbation and parameter uncertainties. In order to reduce the conservatism brought by full-frequency domain approaches, the finite-frequency technique is employed to design a FE observer that can estimate the magnitude of faults. To eliminate/reduce the impact of faults on system performance, an adaptive event-triggered fault-tolerant consensus controller is then developed, which adjusts the consensus protocol based on the FE information. With the developed distributed fault-tolerant protocol and adaptive event-triggered control scheme, the agents can reach consensus in the presence of system faults and the transmission of unnecessary information in the control channels is avoided. The proposed triggering scheme offers certain advantages over existing results in balancing desired consensus performance and improving network utilization. By constructing a parameter-dependent Lyapunov function, a sufficient condition for designing the consensus controller gain and the adjustment matrix can be derived in the form of linear matrix inequality. Finally, two simulation examples are included to illustrate the effectiveness of the obtained theoretical results.

This paper focuses on the problem of distributed fault detection and leader-following output consensus for heterogeneous multiagent systems subject to deception attacks. During the information exchange and dissemination, a malicious attacker can make full use of specialized computer technology and launch stochastic deception attacks against some vulnerable agents over the network. The attack signals in actual operation tend to be energy-constrained, and Bernoulli distribution can be used to describe the random features. Taking the attack information into account, the distributed fault detection observer and the dynamic consensus compensator are designed in two separate steps. In order to reduce unnecessary information transmission, a dynamic event-triggered mechanism with output-dependent threshold is introduced to the adjustment of consensus protocol. According to Lyapunov stability theory and linear matrix inequality (LMI) techniques, sufficient conditions are derived for developing the model gains of the observer and the compensator. Finally, a simulation example of RLC circuit systems is provided to illustrate the effectiveness of the obtained theoretical results.

Personalized search engine focuses on establishing a user-webpage dynamic model. In this model, users' personalized factors are introduced so that the search engine is better able to provide the user with targeted feedback. This paper constructs user and webpage dynamic vector tables, introduces singular value decomposition analysis in the processes of topic categorization, and extends the traditional PageRank algorithm.