Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficient-inference work has progressed along two axes: reducing the cost of each model invocation through efficient architectures, and reducing serial decoding steps through parallel generation. Hybrid attention backbones address the former, while diffusion language models (dLLMs) pursue the latter via iterative parallel denoising. Combining these advantages remains challenging: AR-to-dLLM conversion often fails to preserve seed-checkpoint capability, and hybrid-attention recurrent states and masking constraints make diffusion training and serving nontrivial. We present FLARE, a systematic conversion framework for hybrid-attention LLMs. Our analysis identifies transfer data quality as the primary determinant of capability preservation, outweighing loss formulation and attention-mask design. The resulting framework combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising. Starting from strong AR checkpoints with limited post-training data, FLARE is competitive with leading open-source dLLMs across model scales and delivers consistent throughput gains over open-source dLLM baselines in single-GPU concurrent serving. Our results further suggest that practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives, motivating joint design of data, objectives, architectures, and inference systems.
Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network
Institute for Space Weather Sciences, New Jersey Institute of Technology（新泽西理工学院空间天气科学研究所）；Department of Computer Science, New Jersey Institute of Technology（新泽西理工学院计算机科学系）；Big Bear Solar Observatory, New Jersey Institute of Technology（新泽西理工学院大熊太阳天文台）；Center for Solar-Terrestrial Research, New Jersey Institute of Technology（新泽西理工学院日地研究中心）；Johns Hopkins University Applied Physics Laboratory（约翰霍普金斯大学应用物理实验室）；Research Center for Astronomy and Applied Mathematics, Academy of Athens（雅典学院天文学与应用数学研究中心）；Department of Astrophysical Sciences, Princeton University（普林斯顿大学天体物理科学系）
RoHyDR: Robust Hybrid Diffusion Recovery for Incomplete Multimodal Emotion Recognition
School of Computer Science and Engineering（计算机科学与工程学院）；South China University of Technology（华南理工大学）；School of Future Technology（未来技术学院）；University of Oxford（牛津大学）；Pengcheng Laboratory（鹏城实验室）；Department of Computer Science（计算机科学系）
Efficient hybrid modeling and sorption model discovery for non-linear advection-diffusion-sorption systems: A systematic scientific machine learning approach
University of Porto（波尔图大学）；Norwegian University of Science and Technology（挪威科技大学）；Massachusetts Institute of Technology（麻省理工学院）
AnomalousNet: A Hybrid Approach with Attention U-Nets and Change Point Detection for Accurate Characterization of Anomalous Diffusion in Video Data
Instituto Universitario de Matemática Pura y Aplicada (IUMPA), Universitat Politècnica de València（瓦伦西亚理工大学纯数学与应用数学大学研究所）；Centro de Investigación en Gestión e Ingeniería de Producción (CIGIP), Universitat Politècnica de València（瓦伦西亚理工大学生产管理与工程研究中心）
Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
Independent Researcher Cambridge, USA（独立研究者 美国剑桥）；Department of Electrophysics National Yang Ming Chiao Tung University Hsinchu, Taiwan（电子物理系 国立阳明交通大学 台北县）
