Multimodal Emotion Recognition in Conversations (MERC) enhances emotional understanding through the fusion of multimodal signals. However, unpredictable modality absence in real-world scenarios significantly degrades the performance of existing methods. Conventional missing-modality recovery approaches, which depend on training with complete multimodal data, often suffer from semantic distortion under extreme data distributions, such as fixed-modality absence. To address this, we propose the Federated Dialogue-guided and Semantic-Consistent Diffusion (FedDISC) framework, pioneering the integration of federated learning into missing-modality recovery. By federated aggregation of modality-specific diffusion models trained on clients and broadcasting them to clients missing corresponding modalities, FedDISC overcomes single-client reliance on modality completeness. Additionally, the DISC-Diffusion module ensures consistency in context, speaker identity, and semantics between recovered and available modalities, using a Dialogue Graph Network to capture conversational dependencies and a Semantic Conditioning Network to enforce semantic alignment. We further introduce a novel Alternating Frozen Aggregation strategy, which cyclically freezes recovery and classifier modules to facilitate collaborative optimization. Extensive experiments on the IEMOCAP, CMUMOSI, and CMUMOSEI datasets demonstrate that FedDISC achieves superior emotion classification performance across diverse missing modality patterns, outperforming existing approaches.

Diffusion-based generative models have long depended on Gaussian priors, with little exploration of alternative distributions. We introduce a Proper Hölder-Kullback Dirichlet framework that uses time-varying multiplicative transformations to define both forward and reverse diffusion processes. Moving beyond conventional reweighted evidence lower bounds (ELBO) or Kullback–Leibler upper bounds (KLUB), we propose two novel divergence measures: the Proper Hölder Divergence (PHD) and the Proper Hölder–Kullback (PHK) divergence, the latter designed to restore symmetry missing in existing formulations. When optimizing our Dirichlet diffusion model with PHK, we achieve a Fréchet Inception Distance (FID) of 2.78 on unconditional CIFAR-10. Comprehensive experiments on natural-image datasets validate the generative strengths of model and confirm PHK’s effectiveness in model training. These contributions expand the diffusion-model family with principled non-Gaussian processes and effective optimization tools, offering new avenues for versatile, high-fidelity generative modeling.

Autonomous aerial vehicles have emerged as critical platforms for 3D environmental mapping, yet existing LiDAR-based systems struggle to balance efficiency and compactness in large-scale scenarios. Conventional designs rigidly mount LiDAR with a narrow vertical field of view, necessitating inefficient vertical maneuvers for coverage. While rotating LiDARs can mitigate this limitation, they are often burdensome for lightweight aerial platforms and require processing more expansive 3D data streams. To address these challenges, we present FLARE, a co-designed aerial exploration system integrating a lightweight actively rotated LiDAR with a hierarchical planning framework. The micro-servo-actuated LiDAR dynamically adjusts its orientation via online planning, effectively expanding its sensing field without incurring substantial system complexity. Moreover, FLARE employs a hierarchical frontier clustering method that supports multilayer coarse-to-fine planning, balancing computational load and exploration performance to ensure efficient operation even in large-scale scenarios. Both simulation and fully onboard real-world experiments validate the system’s effectiveness, demonstrating complete coverage with shorter trajectories and reduced flight time compared to existing methods.

Genomic big data analysis pipelines are bottlenecked with massive data movement between CPU and memory hierarchy. Recently developed Stacked Embedded DRAM (SEDRAM) with high density hybrid bonding offers not only high bandwidth concurrent data accesses, but also highly parallel distributed data processing on the logic layer. However, the complex logical flow and data dependencies pose challenges to existing Near-DRAM Processing (NDP) solutions for analysis such as string pattern matching using FM-Index. In this work, we propose REGAL, a highly scalable and re-programmable solution on SEDRAM memory system. REGAL architecture maximizes intra-query parallelism and enhances occupancy of all components. The efficient data layout and mapping minimizes round-trip communications between processing engines. The programmability of REGAL further enables effective prefetching to support variations in data characteristics and involved algorithms. REGAL demonstrates up-to 17.3x and 70.6x speedup and energy reductions compared to multithreaded CPU implementation for FM-Index queries, while achieving performance comparable to state-of-the-art fixed-function NDP implementation.