Peking University — CS Research

Computer science research from Peking University, spanning machine learning, computer vision, and theoretical computer science.

Sample of the collection (25 of 2,468 items)

• Integrated bionic LiDAR for adaptive 4D machine vision Peking University The human eye achieves high resolution and energy efficiency through adaptive focusing on pertinent details. This natural capability…
• Quantum lattice Boltzmann method for simulating nonlinear fluid dynamics Peking University Quantum computing holds transformative potential for simulating nonlinear physical systems, such as fluid turbulence. However, mapping…
• Computational design of two‐dimensional <scp> MA ₂ Z ₄ </scp> family field‐effect transistor for future Ångström‐scale <scp>CMOS</scp> technology nodes Singapore University of Technology and Design Abstract Advancing complementary metal–oxide–semiconductor (CMOS) technology into the sub‐1‐nm Ångström‐scale technology nodes is…
• Toward Efficient and Accurate Prediction of Phonon‐Limited Carrier Mobility by First Principles Peking University Abstract Carrier mobility refers to the ability of charge carriers to move through a material in response to an applied electric field,…
• Unifying optical gain and electro-optical dynamics in Er-doped thin-film lithium niobate platform Peking University Modulation and amplification are two fundamental processes in optoelectronics. While discrete implementations have achieved widespread…
• An integrated flexible sensor for decoupled omnidirectional strain and human motion monitoring Inner Mongolia University of Technology Omnidirectional strain sensors are of paramount importance in the accurate detection of human movements. The mask printing technology is…
• How to select high-quality health educational short videos on social media? insights from youtube and douyin Peking University BACKGROUND: Social media has become a prominent source of health educational short videos (HESVs), yet their quality varies…
• Causal pathways underlying global soil moisture–precipitation coupling Tsinghua University Surface soil moisture-precipitation (SSM-P) coupling involves complex processes, with sensible heat (SH) and evapotranspiration as…
• Integrated retrieval of water quality parameters using UAV hyperspectral images and satellite imagery: Leveraging deep learning and attention mechanisms for precision Peking University Integrated retrieval of water quality parameters using UAV hyperspectral images and satellite imagery: Leveraging deep learning and…
• Aquatic Topological Liquid Crystal Gel Kirigami University of Science and Technology of China Abstract The development of soft materials capable of intricate shape transformations and exhibiting unique swimming performance in…
• Secure wireless communication of brain–computer interface and mind control of smart devices enabled by space-time-coding metasurface Nanjing University of Information Science and Technology Brain-computer interface (BCI) provides an interconnected pathway between the human brain and external devices and paves a potential…
• Reconfigurable versatile integrated photonic computing chip Peking University Abstract With the rapid development of information technology, artificial intelligence and large-scale models have exhibited exceptional…
• Adaptive-learning physics-assisted light-field microscopy enables day-long and millisecond-scale super-resolution imaging of 3D subcellular dynamics Wuhan National Laboratory for Optoelectronics Long-term and high-spatiotemporal-resolution 3D imaging of living cells remains an unmet challenge for super-resolution microscopy,…
• RL4CO: An Extensive Reinforcement Learning for Combinatorial Optimization Benchmark Korea Advanced Institute of Science and Technology Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and…
• Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark Peking University With the maturity of 3D capture technology, the explosive growth of point cloud data has burdened the storage and transmission process.…
• Machine Learning Predictive Models, Interpretations, and Applications of Metal-Based Catalysts, UV, and Thermal Activation Persulfate-Based Advanced Oxidation Processes Korea University This study develops a machine learning (ML) framework to predict pollutant degradation kinetic constants (k) in persulfate-based…
• On sum rules for semi-leptonic b → c and b → u decays Central China Normal University A bstract The semi-leptonic b → clν processes are receiving a lot of attention, as the lepton flavor universality (LFU) violation has…
• Machine learning for energy band prediction of halide perovskites Peking University Abstract Halide perovskites have emerged as a class of highly promising photovoltaic materials with exceptional optoelectronic…
• Large Language Models Powered Malicious Traffic Detection: Architecture, Opportunities, and Case Study Peking University Malicious traffic detection is a pivotal technology for network security to identify abnormal network traffic and detect network…
• Comparative Analysis of Machine/Deep Learning Models for Single-Step and Multi-Step Forecasting in River Water Quality Time Series Peking University There is a lack of a systematic comparison framework that can assess models in both single-step and multi-step forecasting situations…
• ArtMem: Adaptive Migration in Reinforcement Learning-Enabled Tiered Memory Xiamen University With the increasing memory demands of emerging applications, tiered memory has become a viable solution for reducing data center…
• A novel hybrid neural network of fluid-structure interaction prediction for two cylinders in tandem arrangement Peking University Fluid-structure interaction (FSI) in multibody systems, a non-negligible phenomenon in engineering applications, has been extensively…
• Visual Representation Learning through Causal Intervention for Controllable Image Editing Chongqing University A key challenge for controllable image editing is that visual attributes with semantic meanings are not always independent, resulting in…
• ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration Peking University Closed-loop simulation is crucial for end-to-end autonomous driving. Existing sensor simulation methods (e.g., NeRF and 3DGS)…
• FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering Institute of Computing Technology Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential over traditional rendering techniques,…

Query this set from any AI agent

Agents: a markdown version of this page is at https://publicmcp.org/library/pku.md.