Alibaba Group (United States)

With the rise of smart personal devices, service-oriented human-agent interactions have become increasingly prevalent. This trend highlights the need for personalized dialogue assistants that can understand user-specific traits to accurately interpret requirements and tailor responses to individual preferences. However, existing approaches often overlook the complexities of long-term interactions and fail to capture users’ subjective characteristics. To address these gaps, we present PAL-Bench, a new benchmark designed to evaluate the personalization capabilities of service-oriented assistants in long-term user-agent interactions. In the absence of available real-world data, we develop a multi-step LLM-based synthesis pipeline, which is further verified and refined by human annotators. This process yields PAL-Set, the first Chinese dataset comprising multi-session user logs and dialogue histories, which serves as the foundation for PAL-Bench. Furthermore, to improve personalized service-oriented interactions, we propose H2Memory, a hierarchical and heterogeneous memory framework that incorporates retrieval-augmented generation to improve personalized response generation. Comprehensive experiments on both our PAL-Bench and an external dataset demonstrate the effectiveness of the proposed memory framework.

We introduce Style4D-Bench, the first benchmark suite specifically designed for 4D stylization, with the goal of standardizing evaluation and facilitating progress in this emerging area. Style4D-Bench comprises: 1) a strong baseline that make an initial attempt for 4D stylization, 2) a comprehensive evaluation protocol measuring spatial fidelity, temporal coherence, and multi-view consistency through both perceptual and quantitative metrics, and 3) a curated collection of high-resolution dynamic 4D scenes with diverse motions and complex backgrounds. To establish a strong baseline, we present Style4D, a novel framework built upon 4D Gaussian Splatting. It consists of three key components: a basic 4DGS scene representation to capture reliable geometry, a Style Gaussian Representation that leverages lightweight per-Gaussian MLPs for temporally and spatially aware appearance control, and a Holistic Geometry-Preserved Style Transfer module designed to enhance spatio-temporal consistency via contrastive coherence learning and structural content preservation. Extensive experiments on Style4D-Bench demonstrate that Style4D achieves state-of-the-art performance in 4D stylization, producing fine-grained stylistic details with stable temporal dynamics and consistent multi-view rendering. We expect Style4D-Bench to become a valuable resource for benchmarking and advancing research in stylized rendering of dynamic 3D scenes.

High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges. The online construction of HD maps using on-board sensors has emerged as a promising solution; however, these methods can be impeded by incomplete data due to occlusions and inclement weather, while their performance in distant regions remains unsatisfying. This paper proposes PriorDrive to address these limitations by directly harnessing the power of various vectorized prior maps, significantly enhancing the robustness and accuracy of online HD map construction. Our approach integrates a variety of prior maps uniformly, such as OpenStreetMap's Standard Definition Maps (SD maps), outdated HD maps from vendors, and locally constructed maps from historical vehicle data. To effectively integrate such prior information into online mapping models, we introduce a Hybrid Prior Representation (HPQuery) that standardizes the representation of diverse map elements. We further propose a Unified Vector Encoder (UVE), which employs fused prior embedding and a dual encoding mechanism to encode vector data. To improve the UVE's generalizability and performance, we propose a segment-level and point-level pre-training strategy that enables the UVE to learn the prior distribution of vector data. Through extensive testing on the nuScenes, Argoverse 2 and OpenLane-V2, we demonstrate that PriorDrive is highly compatible with various online mapping models and substantially improves map prediction capabilities. The integration of prior maps through PriorDrive offers a robust solution to the challenges of single-perception data, paving the way for more reliable autonomous driving.

Large Language Models (LLMs) increasingly leverage Federated Learning (FL) to utilize private, task-specific datasets for fine-tuning while preserving data privacy. However, while federated LLM frameworks effectively enable collaborative training without raw data sharing, they critically lack built-in mechanisms for regulatory compliance like GDPR’s right to be forgotten. Integrating private data heightens concerns over data quality and long-term governance, yet existing distributed training frameworks offer no principled way to selectively remove specific client contributions post-training. Due to distributed data silos, stringent privacy constraints, and the intricacies of interdependent model aggregation, federated LLM unlearning is significantly more complex than centralized LLM unlearning. To address this gap, we introduce Oblivionis, a lightweight learning and unlearning framework that enables clients to selectively remove specific private data during federated LLM training, enhancing trustworthiness and regulatory compliance. By unifying FL and unlearning as a dual optimization objective, we incorporate 6 FL and 5 unlearning algorithms for comprehensive evaluation and comparative analysis, establishing a robust pipeline for federated LLM unlearning. Extensive experiments demonstrate that Oblivionis outperforms local training, achieving a robust balance between forgetting efficacy and model utility, with cross-algorithm comparisons providing clear directions for future LLM development.

Generative AI, especially LLM, is driving a fundamental shift in software paradigms, prompting cloud providers to build more efficient serving infrastructures. To meet the computational demands of emerging software, modern CPU processors are integrating Accelerator Units (AU) in the pipeline to accelerate key operations, such as Intel AMX for matrix multiplication. Current practices that dedicate AU-enabled CPU exclusively to LLM serving lead to significant resource waste and inferior efficiency. To this end, sharing AU-enabled CPU with general workloads is necessary to harvest redundant resources and improve platform performance-per-watt. However, perfectly sharing AU can be challenging since they introduce three-dimensional variations: variable usage patterns, compulsory frequency interferences, and dissimilar resource bounds. Existing resource managers are oblivious to complex Accelerator Unit Variations (AUV), resulting in performance and efficiency degradations of up to 50 % in shared environments. Therefore, this paper introduces AUM, a novel AU-aware resource manager designed to handle AUV and maximize the efficiency of shared processors. AUM has two cooperative components with three stages for three-dimensional AUV. The background profiler characterizes the usage, frequency, and resource information into a discrete model, guiding the runtime controller to analyze usage-aware requirements, select frequency-aware divisions, and make bound-aware resource decisions. Through extensive evaluations on production AU-enabled CPUs, we show that AUM improves CPU efficiency by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$4.7-8.8 \%$</tex> while maintaining high-performance AU applications by reducing SLO violations by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{7 - 1 1 \%}$</tex> compared with state-of-the-art resource managers.

Lane-level maps are increasingly preferred over Standard-Definition (SD) and High-Definition (HD) maps, offering a better trade-off among detail richness, coverage breadth, and data freshness. However, constructing city-scale lane-level maps remains time-consuming and labor-intensive. To address these challenges, this letter presents an automated mapping framework that fuses crowdsourced trajectories with satellite imagery to enable scalable and accurate map generation. Our approach begins by mining billions of trajectories to extract the geometric and topological structure of road networks. To enrich feature representation, we introduce an effective multimodal fusion mechanism that integrates trajectory data with satellite images, leveraging the complementary strengths of both modalities. Furthermore, a spatiotemporal prior-fusion decoding strategy is proposed to enhance the accuracy and consistency of vectorized map element perception. Finally, a globally consistent, vectorized lane-level map is generated by synthesizing the geometric and semantic output of the perception pipeline. The proposed method achieves the state-of-the-art mean average precision (mAP) on both a large-scale self-curated dataset and Argoverse 2. Having processed over one million kilometers of road networks, the system demonstrates significant scalability and practicality for real-world lane-level mapping applications.

Falciform ligament appendagitis is an exceedingly rare cause of acute abdominal pain resulting from inflammation and infarction of the falciform ligament’s fatty appendage. Its presentation often mimics more common causes of acute abdomen, making diagnosis challenging. We report the case of a 36-year-old Bangladeshi male with no prior medical history who presented with a four-day history of severe epigastric pain radiating to the right upper quadrant (RUQ). Clinical examination revealed localized tenderness and a palpable soft, well-circumscribed swelling, with laboratory investigations within normal limits except for mild leukocytosis and a slightly elevated alanine aminotransferase (ALT). Initial ultrasound suggested a rectus sheath hematoma; however, contrast-enhanced CT imaging demonstrated a fat-density lesion adjacent to the falciform ligament with surrounding inflammatory stranding, consistent with falciform ligament appendagitis. The patient was managed conservatively with analgesia, intravenous fluids, and supportive care, resulting in progressive improvement and complete resolution of symptoms by hospital day 4 without surgical intervention.

ABSTRACT Barium-substituted cobalt ferrite nanoparticles were synthesized by using the sol–gel auto-combustion method. X-ray diffraction analysis confirmed a single-phase cubic spinel structure, and a phase transformation to an orthorhombic crystal structure was observed after substituting Ba2 + ions.‏ The crystallite size and lattice strain were estimated using the Williamson-Hall method.‏ HR-SEM was employed to examine morphology, and the grain size was calculated by fitting the size histogram with a log-normal distribution. The energy dispersive X-ray spectrum revealed stoichiometric cation ratios. Fourier transform infrared revealed prominent absorption peaks between 624 and 406 cm − 1, confirming the formation of a ferrite structure. The optical energy band gap, ranging from 1.9 to 2.8 eV, suggests potential applications in the water purification process. The observed appropriate values of the coercivity, saturation magnetization, and squareness ratio of the prepared partial Ba-substituted cobalt ferrite nanoparticles make them suitable for magnetic recording and memory devices.