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
Demo Data from EDBT 2026 / reviewers in the wild / expert

Dingzhong Cai

dblp:411/7923 · DBLP profile ↗
← Back
3ranked-venue papers
2as first author
3since 2021 · last 2026
—ORCID · none

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

Artificial intelligence and machine learning · 3 · 2 first-author · 3 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author · 1 since 2021

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.

Artificial intelligence
1 paper
Optimization for machine learning · 67% Multi-agent systems · 33%

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

TopicWeightPapersLastEvidence papers
Machine learning › Optimization for machine learning
hyperparameter optimization		 1.012026
PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract) · AAAI 2026
Knowledge, reasoning and agents › Multi-agent systems
imperfect information games		 1.012026
PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract) · AAAI 2026
Machine learning › Optimization for machine learning › hyperparameter optimization
population-based training		 1.012026
PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract) · AAAI 2026

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

population-based training · 1.0deep CFR · 1.0
YearPublicationVenuePosition
2026 PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract)
abstract
Deep CFR enables end-to-end approximation of Nash equilibria in imperfect-information games(IIGs) but is sensitive to hyperparameters, making manual tuning inefficient. To address this, we propose PT-DCFR, which integrates Population-Based Training(PBT) with Deep CFR to dynamically optimize hyperparameters during training. Building upon this, we further introduce P2T-DCFR, which decouples parameter selection from model performance.
Dingzhong Cai, Huale Li, Shuhan Qi, Jiajia Zhang 0001
 AAAI1
2026 Semi-supervised nighttime pedestrian tracking via dual teachers and VLM-guided semantic enhancement
Dingzhong Cai, Wending Yan, Chunrong Hua, Dawei Dong
 Pattern Recognit.1
2025 FGLight: Learning Neighbor-level Information for Traffic Signal Control
Huale Li, Shuhan Qi, Jiajia Zhang 0001, Dingzhong Cai
 AAMAS5