Search

Code coverage analysis has been widely adopted in the continuous integration of open-source and industry software repositories to monitor the adequacy of regression test suites. However, computing code coverage can be costly, introducing significant overhead during test execution. Plus, re-collecting code coverage for the entire test suite is usually unnecessary when only a part of the coverage data is affected by code changes. While regression test selection (RTS) techniques exist to select a subset of tests whose behaviors may be affected by code changes, they are not compatible with code coverage analysis techniques -- that is, simply executing RTS-selected tests leads to incorrect code coverage results. In this paper, we present the first incremental code coverage analysis technique, which speeds up code coverage analysis by executing a minimal subset of tests to update the coverage data affected by code changes. We implement our technique in a tool dubbed iJaCoCo, which builds on Ekstazi and JaCoCo -- the state-of-the-art RTS and code coverage analysis tools for Java. We evaluate iJaCoCo on 1,122 versions from 22 open-source repositories and show that iJaCoCo can speed up code coverage analysis time by an average of 1.86x and up to 8.20x compared to JaCoCo., Comment: Accepted as a conference paper at ASE 2024

The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. However, creating such datasets is challenging: collecting robot manipulation data in diverse environments poses logistical and safety challenges and requires substantial investments in hardware and human labour. As a result, even the most general robot manipulation policies today are mostly trained on data collected in a small number of environments with limited scene and task diversity. In this work, we introduce DROID (Distributed Robot Interaction Dataset), a diverse robot manipulation dataset with 76k demonstration trajectories or 350 hours of interaction data, collected across 564 scenes and 84 tasks by 50 data collectors in North America, Asia, and Europe over the course of 12 months. We demonstrate that training with DROID leads to policies with higher performance and improved generalization ability. We open source the full dataset, policy learning code, and a detailed guide for reproducing our robot hardware setup., Comment: Project website: https://droid-dataset.github.io/

On-chip optical neural networks (ONNs) have recently emerged as an attractive hardware accelerator for deep learning applications, characterized by high computing density, low latency, and compact size. As these networks rely heavily on massive matrix multiplication, photonic computing cores for matrix computation become crucial components for on-chip ONNs, which harness the degree of freedoms (DOFs) in photonics including space, wavelength and mode dimensions. However, previous photonic computing devices have not fully utilized the orthogonality and the conversion characteristic of the waveguide modes, which as we show here, allows for the simultaneous parallel computing of several independent matrix-vector multiplications within the same device. In this work, we propose an inverse-designed photonic computing core for parallel matrix-vector multiplication. The matrices are implemented through a mode conversion process, where the input fundamental modes are simultaneously converted into several orthogonal output modes. Specifically, we target the complex-valued conversion matrices between input and output modes and inversely design the dielectric distribution within the device to achieve parallel matrix-vector multiplication. As a demonstration, the proposed photonic computing core supports simultaneous parallel computing of two independent matrix-vector multiplications, with an ultra-compact footprint and high computing precision (relative error < 8%) at 1550 nm wavelength. The inverse-designed photonic computing devices hold great potential for high-performance on-chip ONNs with low energy consumption and high computing density.

Large Language models (LLMs) usually rely on extensive training datasets. In the financial domain, creating numerical reasoning datasets that include a mix of tables and long text often involves substantial manual annotation expenses. To address the limited data resources and reduce the annotation cost, we introduce FinLLMs, a method for generating financial question-answering data based on common financial formulas using Large Language Models. First, we compile a list of common financial formulas and construct a graph based on the variables these formulas employ. We then augment the formula set by combining those that share identical variables as new elements. Specifically, we explore formulas obtained by manual annotation and merge those formulas with shared variables by traversing the constructed graph. Finally, utilizing GPT-3.5, we generate financial question-answering data that encompasses both tabular information and long textual content, building on the collected formula set. Our experiments demonstrate that synthetic data generated by FinLLMs effectively enhances the performance of several large-scale numerical reasoning models in the financial domain, outperforming two established benchmark financial question-answering datasets., Comment: Under submission of IEEE Transactions

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train generalist X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. More details can be found on the project website https://robotics-transformer-x.github.io., Comment: Project website: https://robotics-transformer-x.github.io

Manipulation of tissue with surgical tools often results in large deformations that current methods in tracking and reconstructing algorithms have not effectively addressed. A major source of tracking errors during large deformations stems from wrong data association between observed sensor measurements with previously tracked scene. To mitigate this issue, we present a surgical perception framework, SuPerPM, that leverages learning-based non-rigid point cloud matching for data association, thus accommodating larger deformations. The learning models typically require training data with ground truth point cloud correspondences, which is challenging or even impractical to collect in surgical environments. Thus, for tuning the learning model, we gather endoscopic data of soft tissue being manipulated by a surgical robot and then establish correspondences between point clouds at different time points to serve as ground truth. This was achieved by employing a position-based dynamics (PBD) simulation to ensure that the correspondences adhered to physical constraints. The proposed framework is demonstrated on several challenging surgical datasets that are characterized by large deformations, achieving superior performance over state-of-the-art surgical scene tracking algorithms.

Towards flexible object-centric visual perception, we propose a one-shot instance-aware object keypoint (OKP) extraction approach, AnyOKP, which leverages the powerful representation ability of pretrained vision transformer (ViT), and can obtain keypoints on multiple object instances of arbitrary category after learning from a support image. An off-the-shelf petrained ViT is directly deployed for generalizable and transferable feature extraction, which is followed by training-free feature enhancement. The best-prototype pairs (BPPs) are searched for in support and query images based on appearance similarity, to yield instance-unaware candidate keypoints.Then, the entire graph with all candidate keypoints as vertices are divided to sub-graphs according to the feature distributions on the graph edges. Finally, each sub-graph represents an object instance. AnyOKP is evaluated on real object images collected with the cameras of a robot arm, a mobile robot, and a surgical robot, which not only demonstrates the cross-category flexibility and instance awareness, but also show remarkable robustness to domain shift and viewpoint change., Comment: Submitted to IEEE ICRA 2024 as a contributed paper

We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program space. To bridge the large generalization gap between proxy and target tasks, we also introduce program selection and simplification strategies. Our method discovers a simple and effective optimization algorithm, $\textbf{Lion}$ ($\textit{Evo$\textbf{L}$ved S$\textbf{i}$gn M$\textbf{o}$me$\textbf{n}$tum}$). It is more memory-efficient than Adam as it only keeps track of the momentum. Different from adaptive optimizers, its update has the same magnitude for each parameter calculated through the sign operation. We compare Lion with widely used optimizers, such as Adam and Adafactor, for training a variety of models on different tasks. On image classification, Lion boosts the accuracy of ViT by up to 2% on ImageNet and saves up to 5x the pre-training compute on JFT. On vision-language contrastive learning, we achieve 88.3% $\textit{zero-shot}$ and 91.1% $\textit{fine-tuning}$ accuracy on ImageNet, surpassing the previous best results by 2% and 0.1%, respectively. On diffusion models, Lion outperforms Adam by achieving a better FID score and reducing the training compute by up to 2.3x. For autoregressive, masked language modeling, and fine-tuning, Lion exhibits a similar or better performance compared to Adam. Our analysis of Lion reveals that its performance gain grows with the training batch size. It also requires a smaller learning rate than Adam due to the larger norm of the update produced by the sign function. Additionally, we examine the limitations of Lion and identify scenarios where its improvements are small or not statistically significant. Lion is also successfully deployed in production systems such as Google search ads CTR model., Comment: 30 pages, Lion is successfully deployed in production systems. We also add comparison with other automatically discovered optimizers

The ability to control heat transport with electrical signals has been an outstanding challenge due to the lack of efficient electrothermal materials. Previous attempts have mainly concentrated on phase-change and layered materials and encountered various problems such as low thermal conductivities and modest on/off ratios. Here, we demonstrate a graphene-based electrothermal switch enabling electrically tuneable heat flow. The device uses reversible electro-intercalation of ions to modulate the in-plane thermal conductivity of graphene film by over thirteen-fold via electrically tuneable phonon scattering. We anticipate that our results could provide a realistic pathway for adaptive thermal transport enabling a new class of electrically driven thermal devices which would find a broad spectrum of applications in aerospace and microelectronics., Comment: 14 pages, 5 figures

The topological structure associated with the branchpoint singularity around an exceptional point (EP) provides new tools for controlling the propagation of electromagnetic waves and their interaction with matter. To date, observation of EPs in light-matter interactions has remained elusive and has hampered further progress in applications of EP physics. Here, we demonstrate the emergence of EPs in the electrically controlled interaction of light with a collection of organic molecules in the terahertz regime at room temperature. We show, using time-domain terahertz spectroscopy, that the intensity and phase of terahertz pulses can be controlled by a gate voltage which drives the device across the EP. This fully electrically-tuneable system allows reconstructing the Riemann surface associated with the complex energy landscape and provides a topological control of light by tuning the loss-imbalance and frequency detuning of interacting modes. We anticipate that our work could pave the way for new means of dynamic control on the intensity and phase of terahertz field, developing topological optoelectronics, and studying the manifestations of EP physics in the quantum correlations of the light emitted by a collection of emitters coupled to resonators., Comment: 17 pages, 4 figures

Google has a monolithic codebase with tens of millions build targets. Each build target specifies the information that is needed to build a software artifact or run tests. It is common to execute a subset of build targets at each revision and make sure that the change does not break the codebase. Google's build service system uses Bazel to build targets. Bazel takes as input a build that specifies the execution context, flags and build targets to run. The outputs are the build libraries, binaries or test results. To be able to support developer's daily activities, the build service system runs millions of builds per day. It is a known issue that a build with many targets could run out of the allocated memory or exceed its execution deadline. This is problematic because it reduces the developer's productivity, e.g. code submissions or binary releases. In this paper, we propose a technique that predicts the memory usage and executor occupancy of a build. The technique batches a set of targets such that the build created with those targets does not run out of memory or exceed its deadline. This approach significantly reduces the number of builds that run out of memory or exceed the deadlines, hence improving developer's productivity.

This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire (bounded) input spaces, and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art model counters. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1-score) when evaluated in the common setting of using training and test datasets - even when the training dataset is much smaller than the test dataset - indicating the seeming simplicity of learning relational properties. However, MCML metrics based on model counting show that the performance can degrade substantially when tested against the entire (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true performance.

Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, such as healthcare or self-driving cars is hindered by their inability to provide safety guarantees or to expose the inner workings of the model in a human understandable form. We present Mo\"ET, a novel model based on Mixture of Experts, consisting of decision tree experts and a generalized linear model gating function. Thanks to such gating function the model is more expressive than the standard decision tree. To support non-differentiable decision trees as experts, we formulate a novel training procedure. In addition, we introduce a hard thresholding version, Mo\"ETH, in which predictions are made solely by a single expert chosen via the gating function. Thanks to that property, Mo\"ETH allows each prediction to be easily decomposed into a set of logical rules in a form which can be easily verified. While Mo\"ET is a general use model, we illustrate its power in the reinforcement learning setting. By training Mo\"ET models using an imitation learning procedure on deep RL agents we outperform the previous state-of-the-art technique based on decision trees while preserving the verifiability of the models. Moreover, we show that Mo\"ET can also be used in real-world supervised problems on which it outperforms other verifiable machine learning models.

Deep Neural Networks (DNN) are increasingly used in a variety of applications, many of them with substantial safety and security concerns. This paper introduces DeepCheck, a new approach for validating DNNs based on core ideas from program analysis, specifically from symbolic execution. The idea is to translate a DNN into an imperative program, thereby enabling program analysis to assist with DNN validation. A basic translation however creates programs that are very complex to analyze. DeepCheck introduces novel techniques for lightweight symbolic analysis of DNNs and applies them in the context of image classification to address two challenging problems in DNN analysis: 1) identification of important pixels (for attribution and adversarial generation); and 2) creation of 1-pixel and 2-pixel attacks. Experimental results using the MNIST data-set show that DeepCheck's lightweight symbolic analysis provides a valuable tool for DNN validation.

Fault localization is a popular research topic and many techniques have been proposed to locate faults in imperative code, e.g. C and Java. In this paper, we focus on the problem of fault localization for declarative models in Alloy -- a first order relational logic with transitive closure. We introduce AlloyFL, the first set of fault localization techniques for faulty Alloy models which leverages multiple test formulas. AlloyFL is also the first set of fault localization techniques at the AST node granularity. We implements in AlloyFL both spectrum-based and mutation-based fault localization techniques, as well as techniques that are based on Alloy's built-in unsat core. We introduce new metrics to measure the accuracy of AlloyFL and systematically evaluate AlloyFL on 38 real faulty models and 9000 mutant models. The results show that the mutation-based fault localization techniques are significantly more accurate than other types of techniques.