Guandao Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Guandao Yang has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Leonidas Guibas
Stanford University, Stanford, USA
4 shared publications - Bharath Hariharan
Cornell University
3 shared publications - Gordon Wetzstein
Stanford University
3 shared publications - Harald Haraldsson
Cornell Tech, New York, New York, USA
2 shared publications Katie Luo
2 shared publications- Serge Belongie
University of Copenhagen
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Agentic Graphics
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessAgentic Graphics
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
MeshFlow: Mesh Generation with Equivariant Flow Matching
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessMeshFlow: Mesh Generation with Equivariant Flow Matching
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Robust Symmetry Detection via Riemannian Langevin Dynamics
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessRobust Symmetry Detection via Riemannian Langevin Dynamics
- 24 November 2024
- Published by Springer Nature
- p. 297-314
BlenderAlchemy: Editing 3D Graphics with Vision-Language Models
- 24 November 2024
- Published by Springer Nature
- p. 297-314
BlenderAlchemy: Editing 3D Graphics with Vision-Language Models
- Open Access
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Neural Control Variates with Automatic Integration
This paper presents a method to leverage arbitrary neural network architecture for control variates. Control variates are crucial in reducing the variance of Monte Carlo integration, but they hinge on finding a function that both correlates with the integrand and has a known analytical integral. Traditional approaches rely on heuristics to choose this function, which might not be expressive enough to correlate well with the integrand. Recent research alleviates this issue by modeling the integrands with a learnable parametric model, such as a neural network. However, the challenge remains in creating an expressive parametric model with a known analytical integral. This paper proposes a novel approach to construct learnable parametric control variates functions from arbitrary neural network architectures. Instead of using a network to approximate the integrand directly, we employ the network to approximate the anti-derivative of the integrand. This allows us to use automatic differentiation to create a function whose integration can be constructed by the antiderivative network. We apply our method to solve partial differential equations using the Walk-on-sphere algorithm [Sawhney and Crane 2020]. Our results indicate that this approach is unbiased using various network architectures and achieves lower variance than other control variate methods.
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessNeural Control Variates with Automatic Integration
This paper presents a method to leverage arbitrary neural network architecture for control variates. Control variates are crucial in reducing the variance of Monte Carlo integration, but they hinge on finding a function that both correlates with the integrand and has a known analytical integral. Traditional approaches rely on heuristics to choose this function, which might not be expressive enough to correlate well with the integrand. Recent research alleviates this issue by modeling the integrands with a learnable parametric model, such as a neural network. However, the challenge remains in creating an expressive parametric model with a known analytical integral. This paper proposes a novel approach to construct learnable parametric control variates functions from arbitrary neural network architectures. Instead of using a network to approximate the integrand directly, we employ the network to approximate the anti-derivative of the integrand. This allows us to use automatic differentiation to create a function whose integration can be constructed by the antiderivative network. We apply our method to solve partial differential equations using the Walk-on-sphere algorithm [Sawhney and Crane 2020]. Our results indicate that this approach is unbiased using various network architectures and achieves lower variance than other control variate methods.
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Neural Caches for Monte Carlo Partial Differential Equation Solvers
This paper presents a method that uses neural networks as a caching mechanism to reduce the variance of Monte Carlo Partial Differential Equation solvers, such as the Walk-on-Spheres algorithm [Sawhney and Crane 2020]. While these Monte Carlo PDE solvers have the merits of being unbiased and discretization-free, their high variance often hinders real-time applications. On the other hand, neural networks can approximate the PDE solution, and evaluating these networks at inference time can be very fast. However, neural-network-based solutions may suffer from convergence difficulties and high bias. Our hybrid system aims to combine these two potentially complementary solutions by training a neural field to approximate the PDE solution using supervision from a WoS solver. This neural field is then used as a cache in the WoS solver to reduce variance during inference. We demonstrate that our neural field training procedure is better than the commonly used self-supervised objectives in the literature. We also show that our hybrid solver exhibits lower variance than WoS with the same computational budget: it is significantly better for small compute budgets and provides smaller improvements for larger budgets, reaching the same performance as WoS in the limit.
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessNeural Caches for Monte Carlo Partial Differential Equation Solvers
This paper presents a method that uses neural networks as a caching mechanism to reduce the variance of Monte Carlo Partial Differential Equation solvers, such as the Walk-on-Spheres algorithm [Sawhney and Crane 2020]. While these Monte Carlo PDE solvers have the merits of being unbiased and discretization-free, their high variance often hinders real-time applications. On the other hand, neural networks can approximate the PDE solution, and evaluating these networks at inference time can be very fast. However, neural-network-based solutions may suffer from convergence difficulties and high bias. Our hybrid system aims to combine these two potentially complementary solutions by training a neural field to approximate the PDE solution using supervision from a WoS solver. This neural field is then used as a cache in the WoS solver to reduce variance during inference. We demonstrate that our neural field training procedure is better than the commonly used self-supervised objectives in the literature. We also show that our hybrid solver exhibits lower variance than WoS with the same computational budget: it is significantly better for small compute budgets and provides smaller improvements for larger budgets, reaching the same performance as WoS in the limit.
- Open Access
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Geometry Processing with Neural Fields
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessGeometry Processing with Neural Fields
- Open Access
Residual Aligned: Gradient Optimization for Non-Negative Image Synthesis
In this work, we address an important problem of optical see through (OST) augmented reality: non-negative image synthesis. Most of the image generation methods fail under this condition, since they assume full control over each pixel and cannot create darker pixels by adding light. In order to solve the non-negative image generation problem in AR image synthesis, prior works have attempted to utilize optical illusion to simulate human vision but fail to preserve lightness constancy well under situations such as high dynamic range. In our paper, we instead propose a method that is able to preserve lightness constancy at a local level, thus capturing high frequency details. Compared with existing work, our method shows strong performance in image-to-image translation tasks, particularly in scenarios such as large scale images, high resolution images, and high dynamic range image transfer.
Open AccessResidual Aligned: Gradient Optimization for Non-Negative Image Synthesis
In this work, we address an important problem of optical see through (OST) augmented reality: non-negative image synthesis. Most of the image generation methods fail under this condition, since they assume full control over each pixel and cannot create darker pixels by adding light. In order to solve the non-negative image generation problem in AR image synthesis, prior works have attempted to utilize optical illusion to simulate human vision but fail to preserve lightness constancy well under situations such as high dynamic range. In our paper, we instead propose a method that is able to preserve lightness constancy at a local level, thus capturing high frequency details. Compared with existing work, our method shows strong performance in image-to-image translation tasks, particularly in scenarios such as large scale images, high resolution images, and high dynamic range image transfer.
- Open Access
Stay Positive: Non-Negative Image Synthesis for Augmented Reality
In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image. Most image generation methods, however, are ill-suited to this problem setting, as they make the assumption that one can assign arbitrary color to each pixel. In fact, naive application of existing methods fails even in simple domains such as MNIST digits, since one cannot create darker pixels by adding light. We know, however, that the human visual system can be fooled by optical illusions involving certain spatial configurations of brightness and contrast. Our key insight is that one can leverage this behavior to produce high quality images with negligible artifacts. For example, we can create the illusion of darker patches by brightening surrounding pixels. We propose a novel optimization procedure to produce images that satisfy both semantic and non-negativity constraints. Our approach can incorporate existing state-of-the-art methods, and exhibits strong performance in a variety of tasks including image-to-image translation and style transfer.
Open AccessStay Positive: Non-Negative Image Synthesis for Augmented Reality
In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image. Most image generation methods, however, are ill-suited to this problem setting, as they make the assumption that one can assign arbitrary color to each pixel. In fact, naive application of existing methods fails even in simple domains such as MNIST digits, since one cannot create darker pixels by adding light. We know, however, that the human visual system can be fooled by optical illusions involving certain spatial configurations of brightness and contrast. Our key insight is that one can leverage this behavior to produce high quality images with negligible artifacts. For example, we can create the illusion of darker patches by brightening surrounding pixels. We propose a novel optimization procedure to produce images that satisfy both semantic and non-negativity constraints. Our approach can incorporate existing state-of-the-art methods, and exhibits strong performance in a variety of tasks including image-to-image translation and style transfer.