arXiv subjects

Edward Yang

Publications and source records attributed to Edward Yang.

6 recordsLinked to original sources

arXiv2026

Optimus: A Generic Operator-Level PyTorch Model Transformation Framework

In large-scale industrial applications, deep learning models that power recommendation and ranking have complex and diverse model architectures. These models are continuously developed and refined by large teams of machine learning engineers, rendering manual optimization infeasible. Consequently, graph-based optimization techniques have become an industry standard for boosting performance, with PyTorch FX transformations leading the charge. These transformations typically rely on a set of human-engineered module-level rewrite rules which are not scalable to diverse model architectures. To address this limitation, we introduce Optimus, a general-purpose model transformation framework built in the PyTorch 2.x (PT2) machine learning compiler. With a concise set of predefined patterns, Optimus applies an efficient greedy search algorithm for pattern matching and replacement, while preserving model semantic. It is designed and implemented as a highly customizable and extensible framework integrated into the PT2 stack. Our evaluation shows that the framework can achieve up to 63% speedup, 6% peak memory reduction, and over 400 second compile time decrease for our industry-scale recommendation models compared to baselines. Optimus is open-sourced together with PyTorch 2.x as a customizable model transformation layer.

cs.PF↗

arXiv2024

Rapid, High-resolution and Distortion-free $R_{2}^{*}$ Mapping of Fetal Brain using Multi-echo Radial FLASH and Model-based Reconstruction

Purpose: To develop a rapid, high-resolution and distortion-free technique for simultaneous water-fat separation, $R_{2}^{*}$ and $B_{0}$ mapping of the fetal brain at 3T. Methods: A 2D multi-echo radial FLASH sequence with blip gradients is adapted for data acquisition during maternal free breathing. A calibrationless model-based reconstruction with sparsity constraints is developed to jointly estimate water, fat, $R_{2}^{*}$ and $B_{0}$ field maps directly from k-space. This approach was validated and compared to reference methods using numerical and NIST phantoms and data from nine fetuses between 26 and 36 weeks of gestation age. Results: Both numerical and experimental phantom studies confirm good accuracy and precision. In fetal studies, model-based reconstruction yields quantitative $R_{2}^{*}$ values in close agreement with those from a parallel imaging compressed sensing (PICS) technique using Graph Cut (intra-class correlation coefficient [ICC] = 0.9601), while providing enhanced image detail. Repeated scans confirm good reproducibility (ICC = 0.9213). Compared to multi-echo EPI, the proposed radial technique produces higher-resolution (1.1 $\times$ 1.1 $\times$ 3 mm$^{3}$ vs. 2-3 $\times$ 2-3 $\times$ 3 mm$^{3}$) $R_{2}^{*}$ maps with reduced distortion. Despite of differences in motion, resolution and distortion, $R_{2}^{*}$ values are comparable between the two acquisition strategies (ICC = 0.8049). Additionally, the proposed approach enables synthesis of high-resolution and distortion-free $R_{2}^{*}$-weighted images. Conclusion: This study demonstrates the feasibility of using multi-echo radial FLASH combined with calibrationless model-based reconstruction for motion-robust, distortion-free $R_{2}^{*}$ mapping of the fetal brain at 3T, achieving a nominal resolution of $1.1 \times 1.1 \times 3$ mm$^{3}$ within 2 seconds per slice.

physics.med-ph↗

arXiv2024

A Multimodal Approach to The Detection and Classification of Skin Diseases

According to PBS, nearly one-third of Americans lack access to primary care services, and another forty percent delay going to avoid medical costs. As a result, many diseases are left undiagnosed and untreated, even if the disease shows many physical symptoms on the skin. With the rise of AI, self-diagnosis and improved disease recognition have become more promising than ever; in spite of that, existing methods suffer from a lack of large-scale patient databases and outdated methods of study, resulting in studies being limited to only a few diseases or modalities. This study incorporates readily available and easily accessible patient information via image and text for skin disease classification on a new dataset of 26 skin disease types that includes both skin disease images (37K) and associated patient narratives. Using this dataset, baselines for various image models were established that outperform existing methods. Initially, the Resnet-50 model was only able to achieve an accuracy of 70% but, after various optimization techniques, the accuracy was improved to 80%. In addition, this study proposes a novel fine-tuning strategy for sequence classification Large Language Models (LLMs), Chain of Options, which breaks down a complex reasoning task into intermediate steps at training time instead of inference. With Chain of Options and preliminary disease recommendations from the image model, this method achieves state of the art accuracy 91% in diagnosing patient skin disease given just an image of the afflicted area as well as a patient description of the symptoms (such as itchiness or dizziness). Through this research, an earlier diagnosis of skin diseases can occur, and clinicians can work with deep learning models to give a more accurate diagnosis, improving quality of life and saving lives.

eess.IV↗

arXiv2024

ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection

NeRFs have achieved incredible success in novel view synthesis. However, the accuracy of the implicit geometry is unsatisfactory because the passive static environmental illumination has low spatial frequency and cannot provide enough information for accurate geometry reconstruction. In this work, we propose ActiveNeRF, a 3D geometry reconstruction framework, which improves the geometry quality of NeRF by actively projecting patterns of high spatial frequency onto the scene using a projector which has a constant relative pose to the camera. We design a learnable active pattern rendering pipeline which jointly learns the scene geometry and the active pattern. We find that, by adding the active pattern and imposing its consistency across different views, our proposed method outperforms state of the art geometry reconstruction methods qualitatively and quantitatively in both simulation and real experiments. Code is avaliable at https://github.com/hcp16/active_nerf

cs.CV↗

arXiv2021

ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotation

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.

cs.CV↗

arXiv2019

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks.

cs.LG↗