EDBT 2026 Demo / reviewers in the wild / expert
Kai Yuanqing Xiao
dblp:295/5349
· DBLP profile ↗
4ranked-venue papers
2as first author
2since 2021 · last 2022
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 4 · 2 first-author · 2 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
4 papers |
Trustworthy machine learning · 86% Image recognition and object detection · 11% 3D vision · 4% | |
| Software engineering, system software, and programming languages
1 paper |
Program verification · 100% |
Topics — the 9 heaviest of 9, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Trustworthy machine learning
robustness |
1.8 | 4 | 2022 | 3DB: A Framework for Debugging Computer Vision Models · NeurIPS 2022 Noise or Signal: The Role of Image Backgrounds in Object Recognition · ICLR 2021 Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability · ICLR (Poster) 2019 |
Machine learning › Trustworthy machine learning
interpretability |
0.6 | 1 | 2022 | 3DB: A Framework for Debugging Computer Vision Models · NeurIPS 2022 |
Machine learning › Trustworthy machine learning › dataset bias
background bias |
0.5 | 1 | 2021 | Noise or Signal: The Role of Image Backgrounds in Object Recognition · ICLR 2021 |
Computer vision › Image recognition and object detection
object recognition |
0.5 | 1 | 2021 | Noise or Signal: The Role of Image Backgrounds in Object Recognition · ICLR 2021 |
Machine learning › Trustworthy machine learning › robustness › model robustness evaluation
adversarial robustness evaluation |
0.4 | 1 | 2019 | Evaluating Robustness of Neural Networks with Mixed Integer Programming · ICLR (Poster) 2019 |
Machine learning › Trustworthy machine learning › robustness › certified robustness
certified adversarial robustness |
0.4 | 1 | 2019 | Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability · ICLR (Poster) 2019 |
Machine learning › Trustworthy machine learning › robustness
neural network verification |
0.4 | 1 | 2019 | Evaluating Robustness of Neural Networks with Mixed Integer Programming · ICLR (Poster) 2019 |
Program verification
neural network verification |
0.4 | 1 | 2019 | Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability · ICLR (Poster) 2019 |
Computer vision › 3D vision
photorealistic simulation |
0.2 | 1 | 2022 | 3DB: A Framework for Debugging Computer Vision Models · NeurIPS 2022 |
Methods — techniques the papers use, named apart from their topics
adversarial training · 0.8ReLU stability · 0.8photorealistic simulation · 0.6object recognition · 0.5background analysis · 0.5mixed integer programming · 0.4
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2022 | 3DB: A Framework for Debugging Computer Vision ModelsabstractWe introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation. We demonstrate, through a wide range of use cases, that 3DB allows users to discover vulnerabilities in computer vision systems and gain insights into how models make decisions. 3DB captures and generalizes many robustness analyses from prior work, and enables one to study their interplay. Finally, we find that the insights generated by the system transfer to the physical world. 3DB will be released as a library alongside a set of examples and documentation. We attach 3DB to the submission. Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Yuanqing Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, Ashish Kapoor, Aleksander Madry |
NeurIPS | 7 |
| 2021 | Noise or Signal: The Role of Image Backgrounds in Object Recognition
Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry |
ICLR | 1 |
| 2019 | Evaluating Robustness of Neural Networks with Mixed Integer Programming
Vincent Tjeng, Kai Yuanqing Xiao, Russ Tedrake |
ICLR (Poster) | 2 |
| 2019 | Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability
Kai Yuanqing Xiao, Vincent Tjeng, Nur Muhammad Shafiullah, Aleksander Madry |
ICLR (Poster) | 1 |