Author name cluster

Le Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

TMLR Journal 2025 Journal Article

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Quankai Gao
Qiangeng Xu
Zhe Cao
Ben Mildenhall
Wenchao Ma
Le Chen
Danhang Tang
Ulrich Neumann

Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored. In this paper, we introduce a novel concept, Gaussian flow, which connects the dynamics of 3D Gaussians and pixel velocities between consecutive frames. The Gaussian flow can be obtained efficiently by splatting Gaussian dynamics into the image space. This differentiable process enables direct dynamic supervision from optical flow. Our method significantly benefits 4D dynamic content generation and 4D novel view synthesis with Gaussian Splatting, especially for contents with rich motions that are hard to handle by existing methods. The common color drifting issue that occurs in 4D generation is also resolved with improved Guassian dynamics. Superior visual quality in extensive experiments demonstrates the effectiveness of our method. As shown in our evaluation, GaussianFlow can drastically improve both quantitative and qualitative results for 4D generation and 4D novel view synthesis.

PDF Details

NeurIPS Conference 2024 Conference Paper

CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming

Ali TehraniJamsaz
Arijit Bhattacharjee
Le Chen
Nesreen K. Ahmed
Amir Yazdanbakhsh
Ali Jannesari

Automatic translation of programming languages has garnered renewed interest, driven by recent advancements in large language models (LLMs). Encoder-decoder transformer models, in particular, have shown promise in translating between different programming languages. However, translating between a language and its high-performance computing (HPC) extension remains underexplored due to inherent challenges like complex parallel semantics understanding. In this paper, we introduce CodeRosetta, an encoder-decoder transformer model explicitly designed for translating between programming languages and also their HPC extensions. CodeRosetta is evaluated on C++ to CUDA and Fortran to C++ translation. It employs a customized learning-based framework with tailored pretraining and training objectives that enable it to effectively capture code semantics and parallel structural nuances, allowing for bidirectional code translation. Our results show that CodeRosetta outperforms state-of-the-art baselines in C++ to CUDA translation by 2. 9 BLEU and 1. 72 CodeBLUE points while improving compilation accuracy by 6. 05%. Compared to general closed-source LLMs, our proposed bidirectional learning-based method improves C++ to CUDA translation by 22. 08 BLEU and 14. 39 CodeBLUE with 2. 75% higher compilation accuracy. Finally, CodeRosetta exhibits proficiency in Fortran to parallel C++ translation, marking it, to our knowledge, as the first encoder-decoder model for such a complex translation task, improving CodeBLEU at least by 4. 63 points compared to closed-source LLMs and Open Code LLM.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Identifying Policy Gradient Subspaces

Jan Schneider 0007
Pierre Schumacher
Simon Guist
Le Chen
Daniel F. B. Häufle
Bernhard Schölkopf
Dieter Büchler

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised learning can be accelerated by leveraging the fact that gradients lie in a low-dimensional and slowly-changing subspace. In this paper, we conduct a thorough evaluation of this phenomenon for two popular deep policy gradient methods on various simulated benchmark tasks. Our results demonstrate the existence of such gradient subspaces despite the continuously changing data distribution inherent to reinforcement learning. These findings reveal promising directions for future work on more efficient reinforcement learning, e.g., through improving parameter-space exploration or enabling second-order optimization.

Details

ICRA Conference 2024 Conference Paper

Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization

Le Chen
Weirong Chen
Rui Wang
Marc Pollefeys

As a promising fashion for visual localization, scene coordinate regression (SCR) has seen tremendous progress in the past decade. Most recent methods usually adopt neural networks to learn the mapping from image pixels to 3D scene coordinates, which requires a vast amount of annotated training data. We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for SCR. Despite NeRF’s efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain, which can hinder the regression accuracy or bring unnecessary computational costs with redundant data. These challenges are addressed in three folds in this paper: (1) A NeRF is designed to separately predict uncertainties for the rendered color and depth images, which reveal data reliability at the pixel level. (2) SCR is formulated as deep evidential learning with epistemic uncertainty, which is used to evaluate information gain and scene coordinate quality. (3) Based on the three arts of uncertainties, a novel view selection policy is formed that significantly improves data efficiency. Experiments on public datasets demonstrate that our method could select the samples that bring the most information gain and promote the performance with the highest efficiency.

Details

NeurIPS Conference 2023 Conference Paper

PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis

Ali TehraniJamsaz
Quazi Ishtiaque Mahmud
Le Chen
Nesreen K. Ahmed
Ali Jannesari

The remarkable growth and significant success of machine learning have expanded its applications into programming languages and program analysis. However, a key challenge in adopting the latest machine learning methods is the representation of programming languages which has a direct impact on the ability of machine learning methods to reason about programs. The absence of numerical awareness, aggregate data structure information, and improper way of presenting variables in previous representation works have limited their performances. To overcome the limitations and challenges of current program representations, we propose a novel graph-based program representation called PERFOGRAPH. PERFOGRAPH can capture numerical information and the aggregate data structure by introducing new nodes and edges. Furthermore, we propose an adapted embedding method to incorporate numerical awareness. These enhancements make PERFOGRAPH a highly flexible and scalable representation that can effectively capture programs' intricate dependencies and semantics. Consequently, it serves as a powerful tool for various applications such as program analysis, performance optimization, and parallelism discovery. Our experimental results demonstrate that PERFOGRAPH outperforms existing representations and sets new state-of-the-art results by reducing the error rate by 7. 4% (AMD dataset) and 10% (NVIDIA dataset) in the well-known Device Mapping challenge. It also sets new state-of-the-art results in various performance optimization tasks like Parallelism Discovery and Numa and Prefetchers Configuration prediction.

PDF Details

ICRA Conference 2022 Conference Paper

Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning

Yunke Ao
Le Chen
Florian Tschopp
Michel Breyer
Roland Siegwart
Andrei Cramariuc

Visual-inertial sensors have a wide range of applications in robotics. However, good performance often requires different sophisticated motion routines to accurately calibrate camera intrinsics and inter-sensor extrinsics. This work presents a novel formulation to learn a motion policy to be executed on a robot arm for automatic data collection for calibrating intrinsics and extrinsics jointly. Our approach models the calibration process compactly using model-free deep reinforcement learning to derive a policy that guides the motions of a robotic arm holding the sensor to efficiently collect measurements that can be used for both camera intrinsic calibration and camera-IMU extrinsic calibration. Given the current pose and collected measurements, the learned policy generates the subsequent transformation that optimizes sensor calibration accuracy. The evaluations in simulation and on a real robotic system show that our learned policy generates favorable motion trajectories and collects enough measurements efficiently that yield the desired intrinsics and extrinsics with short path lengths. In simulation, we are able to perform calibrations 10× faster than hand-crafted policies, which transfers to a real-world speed up of 3× over a human expert. The code of this work is publicly available at: https://github.com/ethz-asl/Learn-to-Calibrate.

Details

IS Journal 2020 Journal Article

The Study for Public Management Policy Utility Evaluation and Optimization System under the Framework of Social Computing Perspective

Le Chen
Xianzhi Yuan
Gaoyu Zhang
Qinghua Guo
Wei Liu
Shuyi Zhang

In recent years, in order to rationalize the allocation of social resources and optimize the implementation of public management policies, scholars have conducted in-depth researches on policy effectiveness. However, at present, most of the study is still at the level of using macrolevel qualitative analysis, and lack of quantitative analysis and evaluation system for the effectiveness of policy implementation. The goal of this article is to discuss the utility evaluation system of public management policy from the perspective of social computing. First, based on the data obtained through questionnaire survey, we obtain indicators of the survey data by using factor analysis, and a new BDI (belief–desire–intention) model is created based on the observation indicators, and then the simulation platform is constructed; then, a brand new quantitative analysis method for policy optimization is proposed by using modified logistic functions as a tool. As application, we conducted the case study for the “Targeted poverty alleviation policy in Yulin region” (Guangxi, China), in which the key indicators for the poverty were established, and then the policy optimization suggestions were given based on the results of simulation experiments. This case study has Chinese characteristics, which might be applied to the poverty alleviation work globally.

Details DOI

JBHI Journal 2016 Journal Article

Privacy-Preserving Patient-Centric Clinical Decision Support System on Naïve Bayesian Classification

Ximeng Liu
Rongxing Lu
Jianfeng Ma
Le Chen
Baodong Qin

Clinical decision support system, which uses advanced data mining techniques to help clinician make proper decisions, has received considerable attention recently. The advantages of clinical decision support system include not only improving diagnosis accuracy but also reducing diagnosis time. Specifically, with large amounts of clinical data generated everyday, naïve Bayesian classification can be utilized to excavate valuable information to improve a clinical decision support system. Although the clinical decision support system is quite promising, the flourish of the system still faces many challenges including information security and privacy concerns. In this paper, we propose a new privacy-preserving patient-centric clinical decision support system, which helps clinician complementary to diagnose the risk of patients' disease in a privacy-preserving way. In the proposed system, the past patients' historical data are stored in cloud and can be used to train the naïve Bayesian classifier without leaking any individual patient medical data, and then the trained classifier can be applied to compute the disease risk for new coming patients and also allow these patients to retrieve the top-k disease names according to their own preferences. Specifically, to protect the privacy of past patients' historical data, a new cryptographic tool called additive homomorphic proxy aggregation scheme is designed. Moreover, to leverage the leakage of naïve Bayesian classifier, we introduce a privacy-preserving top-k disease names retrieval protocol in our system. Detailed privacy analysis ensures that patient's information is private and will not be leaked out during the disease diagnosis phase. In addition, performance evaluation via extensive simulations also demonstrates that our system can efficiently calculate patient's disease risk with high accuracy in a privacy-preserving way.

Details DOI