Skip To Main Content
Wei Tsang on Muck Rack

Wei Tsang

As seen in: arXiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Wei Tsang’s profile

Articles by Wei Tsang

Computer Science > Computer Vision and Pattern Recognition

|
By Wei Tsang, Mike Zheng
| arXiv
Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluation underexplored.
Open in Who Shared Issue with article?

Statistics > Machine Learning

|
By Lai Xing, Wei Tsang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (641) Issue with article?

Computer Science > Computer Vision and Pattern Recognition

|
By Wei Tsang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared Issue with article?

Computer Science > Computer Vision and Pattern Recognition

|
By Wei Tsang, Wei Tsang Ooi, Yuang Shi
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (530) Issue with article?

[2601.22538] Learning to Defer in Non-Stationary Time Series via Switching State-Space Models

|
By Lai Xing, Wei Tsang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (631) Issue with article?

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

|
By Lai Xing, Wei Tsang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (452) Issue with article?

Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation

|
By Wei Tsang, Simone Gasparini, Wei Tsang Ooi
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (653) Issue with article?

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

|
By Lai Xing, Wei Tsang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (316) Issue with article?

[2512.09016] Learning to Remove Lens Flare in Event Camera

|
By Lai Xing, Wei Tsang, Lingdong Kong, Jianing Li
| arXiv
Open in Who Shared Issue with article?

[2509.07996] 3D and 4D World Modeling: A Survey

|
By Wei Tsang, Steven C. H
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (368) Issue with article?

[2507.17665] Perspective-Invariant 3D Object Detection

|
By Wei Tsang, Lingdong Kong, Dongyue Lu, Youquan Liu
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (423) Issue with article?

SafeSpect: Safety-First Augmented Reality Heads-up Display for Drone Inspections

|
By Wei Tsang
| arXiv
Open in Who Shared Issue with article?

[2504.12988] Why Ask One When You Can Ask $k$? Two-Stage Learning-to-Defer to a Set of Experts

|
By Lai Xing, Wei Tsang
| arXiv
Open in Who Shared Issue with article?

EventFly: Event Camera Perception from Ground to the Sky

|
By Lai Xing, Wei Tsang, Dongyue Lu, Xiang Xu
| arXiv
Open in Who Shared Issue with article?

LineGS : 3D Line Segment Representation on 3D Gaussian Splatting

|
By Wei Tsang
| arXiv
arXiv:2412.00477 (cs) View PDF HTML (experimental) Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2412.00477 [cs.CV] (or arXiv:2412.00477v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2412.00477 Submission history From: Chenggang Yang [ view email] [v1] Sat, 30 Nov 2024 13:29:36 UTC (15,423 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle...
Open in Who Shared View Duplicates (226) Issue with article?

LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming

|
By Wei Tsang
| arXiv
The Accessibility Forum starts next week! Sign up and join us in September.
Open in Who Shared View Duplicates (636) Issue with article?

The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition

|
By Wei Tsang, Lai Xing
| arXiv
Open in Who Shared Issue with article?

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

|
By Lai Xing, Wei Tsang, Youquan Liu, Lai Xing Ng
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (601) Issue with article?

[2405.05258] Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving

|
By Wei Tsang, Xiang Xu, Jiawei Ren, Wenwei Zhang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (464) Issue with article?

CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening

|
By Hei Yi, Flint Xiaofeng, Wei Tsang
| arXiv
Open in Who Shared Issue with article?

The use of deception in dementia-care robots: Should robots tell "white lies" to limit emotional distress?

|
By Samuel Rhys, Wei Tsang
| arXiv
arXiv:2309.04267 (cs) Download PDF Comments: Subjects: Robotics (cs.RO); Human-Computer Interaction (cs.HC) Cite as: arXiv:2309.04267 [cs.RO] (or arXiv:2309.04267v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2309.04267 Submission history From: Samuel Rhys Cox [ view email] [v1] Fri, 8 Sep 2023 11:27:14 UTC (119 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are...
Open in Who Shared View Duplicates (264) Issue with article?

Prompting a Large Language Model to Generate Diverse Motivational Messages: A Comparison with Human-Written Messages

|
By Wei Tsang, Samuel Rhys
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (673) Issue with article?

Comparing How a Chatbot References User Utterances from Previous Chatting Sessions: An Investigation of Users' Privacy Concerns and Perceptions

|
By Samuel Rhys, Wei Tsang, Yi-Chieh Lee, Wei Tsang Ooi
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (687) Issue with article?

SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning

|
By Wei Tsang
| arXiv
arXiv:2308.02565 (cs) Download a PDF of the paper titled SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning, by Keyu Duan and 6 other authors Download PDF Submission history From: Keyu Duan [ view email] [v1] Thu, 3 Aug 2023 07:00:04 UTC (615 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Links to Code Toggle...
Open in Who Shared View Duplicates (531) Issue with article?

The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation

|
By Lai Xing, Wei Tsang
| arXiv
[Submitted on 27 Jul 2023 ( v1 ), last revised 24 Sep 2024 (this version, v2)] Title:The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation Authors:Lingdong Kong , Yaru Niu , Shaoyuan Xie , Hanjiang Hu , Lai Xing Ng , Benoit R.
Open in Who Shared Issue with article?
Show More