Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Yizhu Zhao

dblp:54/7642 · DBLP profile ↗
← Back
12ranked-venue papers
2as first author
6since 2021 · last 2025
0000-0002-9799-8852ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 4 · 3 since 2021Graphics, computer vision, multimedia, augmented reality and games · 3 · 1 since 2021Human-computer interaction and ubiquitous computing · 2 · 1 first-author · 2 since 2021Computer networks · 1 · 1 since 2021Databases, data management, data science and information retrieval · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Interdisciplinary, comprehensive, and emerging computing
1 paper
Computational science and engineering · 100%
Artificial intelligence
1 paper
Deep learning architectures and training · 50% Trustworthy machine learning · 50%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Computational science and engineering › dynamical systems
dynamical system simulation
0.912025
Towards Generalizable Neural Simulators: Addressing Distribution Shifts Induced by Environmental and Temporal Variations · IJCAI 2025
Machine learning › Trustworthy machine learning › robustness
distribution shift
0.312025
Towards Generalizable Neural Simulators: Addressing Distribution Shifts Induced by Environmental and Temporal Variations · IJCAI 2025
Machine learning › Deep learning architectures and training › neural differential equations
neural ordinary differential equations
0.312025
Towards Generalizable Neural Simulators: Addressing Distribution Shifts Induced by Environmental and Temporal Variations · IJCAI 2025

Methods — techniques the papers use, named apart from their topics

neural stochastic process · 1.7neural ODE · 1.7
YearPublicationVenuePosition
2025 Towards Generalizable Neural Simulators: Addressing Distribution Shifts Induced by Environmental and Temporal Variations
abstract
With advancements in deep learning, neural simulators have become increasingly important for improving the efficiency and effectiveness of simulating complex dynamical systems in various scientific and technological fields. This paper presents a novel neural simulator called Context-informed Polymorphic Neural ODE Processes (CoPoNDP), aimed at addressing the challenges of modeling dynamical systems encountering concurrent environmental and temporal distribution shifts, which are common in real-world scenarios. CoPoNDP employs a context-driven neural stochastic process governed by a combination of basic differential equations in a time-sensitive manner to adaptively modulate the evolution of system states. This allows for flexible adaptation to changing temporal dynamics and generalization across different environments. Extensive experiments conducted on dynamical systems from ecology, chemistry, physics, and energy demonstrate that by effectively utilizing contextual information, CoPoNDP outperforms the state-of-the-art models in handling joint distribution shifts. It also shows robustness in sparse and noisy settings, making it a promising approach for modeling dynamical systems in complex real-world applications.
Jiaxu Cui, Shiang Sun, Yizhu Zhao
IJCAI4
2023 Neu-PCM: Neural-based potential correlation mining for POI recommendation
Jun Zeng 0003, Yizhu Zhao, Junhao Wen 0001
Appl. Intell.3
2023 LGSA: A next POI prediction method by using local and global interest with spatiotemporal awareness
Jun Zeng 0003, Yizhu Zhao, Hongjin Tao, Min Gao 0001, Junhao Wen 0001
Expert Syst. Appl.2
2022 A Flow Prediction Model of Bike-Sharing Based on Cycling Context
Yizhu Zhao, Jun Zeng 0003, Min Gao 0001, Wei Zhou 0028, Junhao Wen 0001
CollaborateCom (1)1
2021 The Missing POI Completion Based on Bidirectional Masked Trajectory Model
Jun Zeng 0003, Yizhu Zhao, Yang Yu 0033, Min Gao 0001, Wei Zhou 0028
CollaborateCom (1)2
2021 PR-RCUC: A POI Recommendation Model Using Region-Based Collaborative Filtering and User-Based Mobile Context
Jun Zeng 0003, Yizhu Zhao, Min Gao 0001, Junhao Wen 0001
Mob. Networks Appl.3
2020 SSET: a dataset for shot segmentation, event detection, player tracking in soccer videos
Na Feng, Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Yizhu Zhao, Yunfeng He
Multim. Tools Appl.5
2016 Dense 3D reconstruction combining depth and RGB information
Hailong Pan, Yawei Luo, Liya Duan, Liu Yi, Yizhu Zhao, Junqing Yu
Neurocomputing7
2014 Trust Inference Path Search Combining Community Detection and Ant Colony Optimization
Hongwei Lu, Zaobin Gan, Yizhu Zhao
WAIM4
2012 Reform and Exploration of the Computer Graphics
abstract
Computer Graphics is an important course for graduate students in computer major. Aiming at the present teaching situation of computer graphics course, combined with an the course characteristics, some educational reform measures, such as adjusting of teaching content, employing more examples in teaching, strengthening the combination of knowledge and practical ability, was proposed. The teaching practices show that these methods can arouse students' learning interest, make the students understand the course better, and obviously improve the quality of teaching.
Yunfeng He, Yizhu Zhao
APSCC2
2012 Some Key Issues of Teaching Reform about Digital Logic
abstract
Based on an analysis of the present teaching situation of Digital Logic course in higher school, this paper points out its existing problems, discusses some key issues and then proposes the ideas such as bringing modern design methodology into course teaching, conducting hierarchical textbooks construction, employing different teaching method and teaching content for different teaching objectives and intensifying the combination of textbook and engineering practical use, so as to improve teaching effectiveness, develop students' interest and enhance their comprehensive practical ability. As the coping strategy to deal with the existing problems of Digital Logic course in higher education, this method has already made certain achievements in both teaching and experiment.
Yizhu Zhao, Yunfeng He
APSCC1
2010 A Dual Binary Image Watermarking Based on Wavelet Domain and Pixel Distribution Features
Hongwei Lu, Yizhu Zhao
MMM3