Yang Zhang

An AF-CRP-enhanced zeroing neural network for time-varying generalized Sylvester matrix equations

Mengyan Xie, Qing-Wen Wang, Yang Zhang

cn, ca (code pays fourni par la source)

Effect of electro-pulsing assisted ultrasonic surface rolling process on microstructure and tribological properties of laser cladding Al1.5Co0.5CrFeNi2(TiB)0.25 composite coatings

Hao Liu, Yang Zhang, Jian Liu, Peijian Chen et autres

cn (code pays fourni par la source)

Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy

Buqing Nie, Yang Zhang, Rong Jin, Zhanxiang Cao et autres

The human nervous system exhibits bilateral symmetry, enabling coordinated and balanced movements. However, existing Deep Reinforcement Learning (DRL) methods for humanoid robots neglect morphological symmetry of the robot, leading to uncoordinated and suboptimal behaviors. Inspired by human motor control, we propose Symmetry …

cn (code pays fourni par la source)

Scene Experts: Specializing in 3D Gaussian Splatting with Adaptive Decomposition

Xiaowen Fu, Yang Zhang, Yuhan Tang, Huazhong Zhang et autres

Anchor-based 3D Gaussian Splatting (GS), exemplified by Scaffold-GS, achieves remarkable storage efficiency through a hybrid explicit-implicit representation. However, their reliance on a single, monolithic network to decode anchor features imposes a severe bottleneck on model capacity, often resulting in blurred details and …

cn (code pays fourni par la source)

Plug-and-Play Parameter-Efficient Tuning of Embeddings for Federated Recommendation

Haochen Yuan, Yang Zhang, Xiang He, Quan Z. Sheng et autres

With the rise of cloud-edge collaboration, recommendation services are increasingly trained in distributed environments. Federated Recommendation (FR) enables such multi-end collaborative training while preserving privacy by sharing model parameters instead of raw data. However, the large number of parameters, primarily due to …

SAME: Spatial-Aware Multimodal Egocentric Human Pose Estimation

Yurong Fu, Peng Dai, Yu Zhang, Feng Yiqiang et autres

Egocentric human pose estimation (HPE) plays a crucial role in immersive applications such as virtual and augmented reality. However, existing methods relying on either visual or sparse inertial data alone often suffer from occlusion or ill-posed problems. In this work, we propose …

cn, hk (code pays fourni par la source)

Subspace-Aware Graph Construction and Contrastive Alignment for Multimodal Recommendation with Large Language Models

Haodong Li, Lianyong Qi, Weiming Liu, Fan Wang et autres

Multimedia content offers additional context for recommender systems to better understand user interests. Existing studies on multimodal recommendation primarily focus on constructing item-item semantic graphs. However, most of these methods capture only shallow semantic structures based on feature similarity and struggle to …

Hyperbolic-Enhanced Mixture-of-Experts Mamba for Sequential Recommendation

Yuwen Liu, Lianyong Qi, Xingyuan Mao, Weiming Liu et autres

Sequential recommendation has emerged as a fundamental task in various domains, aiming to predict a user's next interaction based on historical behavior. Recent advances in deep sequence models, particularly Transformer-based architectures and the more recent Mamba, have substantially pushed the boundaries of …

cn, au, gb, us (code pays fourni par la source)

Pre-Trained Video Generative Models as World Simulators

Haoran He, Yang Zhang, Liang Lin, Zhongwen Xu et autres

Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images), limiting their ability to model interactive and dynamic scenarios. In this …

hk, cn (code pays fourni par la source)

QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression

Lei Huang, Rui Zhang, Jiaming Guo, Yang Zhang et autres

Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured, which poses significant challenges for downstream Verilog code generation. We treat …

cn (code pays fourni par la source)

Right Branches Matter in Failure-based Variable Ordering Heuristics

Yang Zhang, Hongbo Li

Failure-based variable ordering heuristics (VOH) are efficient general-purpose search heuristics for solving constraint satisfaction problems (CSP). They learn from the failures detected during the search and select the variables that are most likely to fail. The current failure-based VOHs, i.e. the failure-rate-based …

cn (code pays fourni par la source)

Keep On Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training

Yang Zhang, Zhanxiang Cao, Buqing Nie, Haoyang Li et autres

Humanoid robots are expected to operate reliably over long horizons while executing versatile whole-body skills. Yet Reinforcement Learning (RL) motion policies typically lose stability under prolonged operation, sensor/actuator noise, and real world disturbances. In this work, we propose a Selective Adversarial Attack …