A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page Not Found
Page not found. Your pixels are in another canvas.
Xingyi Yang
About me
Archive Layout with Content
Posts by Category
Posts by Collection
CV
Experience
Markdown
Page not in menu
This is a page not in th emain menu
Openings
Openings for PhD, postdoc, MPhil, and research assistant positions.
More about me
More about me
Page Archive
Portfolio
Selected Publications
Sitemap
Posts by Tags
Talk map
Talks and presentations
Scalar Activation
Forward, Backward, Update
What a Linear Map Changes
Scalar Computation Graph
A Feature Map Makes XOR Linear
Scalar Accumulation
Teaching
Interactive demos and knowledge-point visualizations for the courses I teach.
Team
Terms and Privacy Policy
Blog posts
Jupyter notebook markdown generator
Posts
Teaching Visualizations
To facilitate the teaching of a certain undergraduate class, I created some visualizations for several basic machine learning algorithms, including K-Means clustering, e.g. These visualizations help students to better understand the underlying concepts of these algorithms and how they work in practice.
Music Sharing: Homesickness

Variational Inference
Widok z ziarnkiem piasku, Wisława Szymborska

Kalman Filter
Omnipotent Youth Society
Omnipotent Youth Society (万能青年旅店,简称万青), Chinese indie band in Hebei. blues rock & indie rock.
Lo Tayou
Lo Tayou (罗大佑), Chinese Musician born in Taiwan.
La Soledad De America Latina, Gabriel García Márquez, 1982 Nobel prize in literature speeches

Why use kernel size of 4 in discriminators?
Why use kernel size of 4 in discriminators? Because of Checkboard artifacts in gradients Link
Ti San Yi Ta, by Xun Lu

Lyrics, Peacock, by Wachi
松糕鞋 松糕鞋 踩上女人街 女人街
Quotes, by Yuan Cui and Shi Su
古之所谓豪杰之士,必有过人之节。人情有所不能忍者,匹夫见辱,拔剑而起,挺身而斗,此不足为勇也。天下有大勇者,卒然临之而不惊,无故加之而不怒。此其所挟持者甚大,而其志甚远也。
The Communist Manifesto, Manifesto of the Communist Party, Karl Marx

On the Battle Lost(Excerpt), Svetlana Alexievich, 2015 Nobel prize in literature speeches

GAN paper reading
Progressive GAN
Progressive growing of GAN
- Start with low-resolution images and then progressively increasing the resolution by adding layers to the network!

Keyword Spotting with hardware constraint
This is a slide about Keyword Spotting with hardware constraint. Some model compression approaches are also introduced to reduce the computational requirement.
portfolio
publications
Single View Metrology in the Wild
16th European Conference on Computer Vision (ECCV2020), 2020
Kalman Optimizer for Consistent Gradient Descent
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2021), 2021
DSRNA: Differentiable Search of Robust Neural Architectures
2021 Conference on Computer Vision and Pattern Recognition (CVPR2021), 2021
Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation
The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL2021), (Long Oral), 2021
On the Generation of Medical Dialogues for COVID-19
The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL2021), long paper, 2021
Neural Point Process for Learning Spatiotemporal Event Dynamics
Conference on Learning for Dynamics and Control (L4DC), 2022
Factorizing Knowledge in Neural Networks
European Conference on Computer Vision (ECCV), 2022
Dataset Distillation via Factorization
Neural Information Processing Systems (NeurIPS), 2022
Towards Stochastic Gradient Variance Reduction by Solving a Filtering Problem
Tiny Papers @ ICLR 2023, 2023
Distribution Shift Inversion for Out-of-Distribution Generalization
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
Conference on Computer Vision and Pattern Recognition (CVPR), (Highlight), 2023
Diffusion Probabilistic Model Made Slim
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
SG-Former: Self-guided Transformer with Evolving Token Reallocation
Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Diffusion Model as Representation Learner
Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Towards Personalized Federated Learning via Heterogeneous Model Reassembly
2023 Conference on Neural Information Processing (NeurIPS), 2023
StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
International Conference on Machine Learning (ICML), 2024
Relation Rectification in Diffusion Model
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Unsegment Anything by Simulating Deformation
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Vista3D: Unravel the 3D Darkside of a Single Image
European Conference on Computer Vision (ECCV), 2024
FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally
European Conference on Computer Vision (ECCV), 2024
Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling
Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
GFlow: Recovering 4D World from Monocular Video
Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
GraphBridge: Towards Arbitrary Transfer Learning in GNNs
International Conference on Learning Representations (ICLR), 2025
Kolmogorov-Arnold Transformer
International Conference on Learning Representations (ICLR), 2025
CoSER: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
Computer Vision and Pattern Recognition (CVPR), (Highlight), 2025
Generative Sparse-View Gaussian Splatting
Computer Vision and Pattern Recognition (CVPR), 2025
Few-shot Implicit Function Generation via Equivariance
Computer Vision and Pattern Recognition (CVPR), (Highlight), 2025
Hash3D: Training-free Acceleration for 3D Generation
Computer Vision and Pattern Recognition (CVPR), 2025
Mixture of Experts Made Intrinsically Interpretable
International Conference on Machine Learning (ICML), 2025
RogSplat: Robust Gaussian Splatting via Generative Priors
IEEE/CVF International Conference on Computer Vision (ICCV), 2025
C4D: 4D Made from 3D through Dual Correspondences
IEEE/CVF International Conference on Computer Vision (ICCV), 2025
OminiControl: Minimal and Universal Control for Diffusion Transformer
IEEE/CVF International Conference on Computer Vision (ICCV), (Highlight), 2025
TreeSplat: Mergeable Tree for Deformable Gaussian Splatting
Neural Information Processing Systems (NeurIPS), 2025
1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
Neural Information Processing Systems (NeurIPS), 2025
Image Editing As Programs with Diffusion Models
Neural Information Processing Systems (NeurIPS), 2025
Test3R: Learning to Reconstruct 3D at Test Time
Neural Information Processing Systems (NeurIPS), 2025
Minute-Long Videos with Dual Parallelisms
AAAI Conference on Artificial Intelligence (AAAI), 2026
DirMoE: Dirichlet-routed Mixture of Experts
International Conference on Learning Representations (ICLR), 2026
SparseD: Sparse Attention for Diffusion Language Models
International Conference on Learning Representations (ICLR), 2026
talks
Talk 1 on Relevant Topic in Your Field
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Tutorial 1 on Relevant Topic in Your Field
Talk 2 on Relevant Topic in Your Field
Conference Proceeding talk 3 on Relevant Topic in Your Field
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.