Haoran Li

JSQKV: Joint Sparsification and Quantization for KV-Cache Compression and Decode Acceleration

Hao Zhang, Xiaoli Gong, Haoran Li, Huayou Su et autres

cn (code pays fourni par la source)

TKN: Transformer-based Keypoint Prediction Network for Real-time Video Prediction

Haoran Li, Xiaolu Li, Pengyuan Zhou, Yanbin Hao

Abstract Video prediction is a complex time-series forecasting task with great potential in many use cases. However, traditional methods prioritize accuracy and overlook slow prediction speeds due to complex model structures, redundant information, and excessive GPU memory consumption. These methods often predict …

cn, dk (code pays fourni par la source)

Alternating Current-Promoted Copper Catalysis for the Construction of Alkynyl Thioethers

Jie Yang, Shabbir Muhammad, Haoran Li, 崔伟灿 et autres

Alkynyl thioethers are versatile intermediates in organic synthesis, and a synthetic strategy involving C-H/S-H oxidative cross-coupling is atom-economical and effective. However, the homocoupling of alkynes is hard to be prevented under aerobic conditions. Herein, we report an oxygen-free electrochemical oxidative coupling of …

cn, us (code pays fourni par la source)

On the Tension Between Optimality and Adversarial Robustness in Policy Optimization

Haoran Li, Jiayu Lv, Congying Han, Zicheng Zhang et autres

Achieving optimality and adversarial robustness in deep reinforcement learning has long been regarded as conflicting goals. Nonetheless, recent theoretical insights presented in CAR suggest a potential alignment, raising the important question of how to realize this in practice. This paper first identifies …

Corrosion mechanism of annealed 2050 Al-Li alloy under the influence of multiple factors

Guofu Xu, Jiawei Fu, Haoran Li, Mengjiao Liu et autres

• The increase of high-angle grain boundaries accelerated corrosion. • The release of stored energy improves corrosion resistance. • The decrease in second phases enhances corrosion resistance. • Second phases have the greatest impact and stored energy have the least impact. The …

cn (code pays fourni par la source)

An Evaluation Method for Penetration Depth of Rubber on Rough Surface and Analysis of Influencing Factors

Haichao Zhou, Zhaohui Hu, Zhiwei Gao, Haoran Li et autres

cn (code pays fourni par la source)

HyMetricScaler: A Multi-Metric-Driven Hybrid Autoscaling Framework for Kubernetes

Yuhong Feng, Jianming Li, Lingjie Li, Haoran Li et autres

Existing Kubernetes autoscaling solutions predominantly rely on single metrics with single-direction scaling (either horizontal or vertical), making it challenging to balance end-to-end latency and CPU utilization effectively. This paper introduces HyMetricScaler, a hybrid autoscaling framework. The framework employs a horizontal scaling component …

cn (code pays fourni par la source)

GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation

Wei Xu, Haoran Li, Baoyuan Ou, Lai Xu et autres

Cross-domain Click-Through Rate prediction aims to tackle the data sparsity and the cold start problems in online advertising systems by transferring knowledge from source domains to a target domain. Most existing methods rely on overlapping users to facilitate this transfer, often focusing …

AI for Landscape Planning: Assessing Surrounding Contextual Impact on GAN-Generated Green Land Layouts

Ran Chen, Xingjian Yi, Jing Zhao, Yueheng He et autres

The development of generative design driven by artificial intelligence algorithms is speedy. There are two research gaps in the current research: 1) Most studies only focus on the relationship between design elements and pay little attention to the external information of the …

cn, us (code pays fourni par la source)

Optimizing beat-wise input for arrhythmia detection using 1-D convolutional neural networks: A real-world ECG study

Sunghan Lee, Guangyao Zheng, Jeonghwan Koh, Haoran Li et autres

BACKGROUNDS AND OBJECTIVES: Cardiac arrhythmias, characterized by irregular heartbeats, are difficult to diagnose in real-world scenarios. Machine learning has advanced arrhythmia detection; however, the optimal number of heartbeats for precise classification remains understudied. This study addresses this using machine learning while assessing …

kr, us (code pays fourni par la source)

Distributed Invariant Kalman Filter for Object-Level Multi-Robot Pose SLAM

Haoying Li, Qingcheng Zeng, Haoran Li, Yanglin Zhang et autres

Cooperative localization and target tracking are essential for multi-robot systems to implement high-level tasks. To this end, we propose a distributed invariant Kalman filter (KF) based on covariance intersection (CI) for effective multi-robot pose estimation. The paper utilizes the object-level measurement models, …

cn, hk (code pays fourni par la source)

Vision‐based adaptive cross‐domain online product recommendation for 3D design models

Xiaoping Zhou, Qin Si, Gen Liu, Zhen Hu et autres

Three-dimensional (3D) digital design is extensively adopted in the architecture, engineering, consulting, operations, and maintenance (AECOM) industry to enhance collaboration among stakeholders. Although recommendation systems are commonly employed to facilitate purchasing in e-commerce websites, none involves recommending online products to users from …

cn (code pays fourni par la source)