This study presents an Actor-Critic Cooperative Compensated Model Predictive Controller$(\text{AC}^3 \text{MPC})$designed to address unknown system dynamics. To avoid the difficulty of modeling highly complex dynamics and ensuring real-time control feasibility and performance, this work uses deep reinforcement learning with a model predictive controller in a cooperative framework to handle unknown dynamics. The model-based controller takes on the primary role as both controllers are provided with predictive information about the other. This improves tracking performance and retention of inherent robustness of the model predictive controller. We evaluate this framework for off-road autonomous driving on unknown deformable terrains that represent sandy deformable soil, sandy and rocky soil, and cohesive clay-like deformable soil. Our findings demonstrate that our controller statistically outperforms standalone model-based and learning-based controllers by upto 29.2% and 10.2%. This framework generalized well over varied and previously unseen terrain characteristics to track longitudinal reference speeds with lower errors. Furthermore, this required significantly less training data compared to purely learning-based controller, while delivering better performance even when under-trained.

We present a generalizable classification approach that leverages Large Language Models (LLMs) to facilitate the detection of implicitly encoded social meaning in conversations.We design a multi-faceted prompt to extract a textual explanation of the reasoning that connects visible cues to underlying social meanings.These extracted explanations or rationales serve as augmentations to the conversational text to facilitate dialogue understanding and transfer.Our empirical results over 2,340 experimental settings demonstrate the significant positive impact of adding these rationales.Our findings hold true for in-domain classification, zero-shot, and few-shot domain transfer for two different social meaning detection tasks, each spanning two different corpora.

Serverless computing is a paradigm that allows application developers to focus on defining functions triggered by events, while the service provider handles resource allocation, isolation, scalability, and orchestration. Function-as-a-Service (FaaS) is a popular implementation of serverless coputing, characterized by short-lived stateless functions. However, current FaaS platforms suffer from high overheads of boot-strapping the process for function execution, which degrade the performance of applications that require low latency and high throughput. Moreover, current FaaS platforms do not support sharing memory among function instances of the same workflow, which limits the efficiency and functionality of applications that rely on data dependencies. In this paper, we propose Ataru, a native function execution virtualization construct that exploits full hardware potential with the provision for shared memory and minimal process bootstrapping overhead, without sacrificing the security offered by virtualization technologies. Ataru consists of two components: Ataru-KVM, a lightweight Virtual Machine Monitor (VMM) based on KVM that supports fast bootup and dynamic suspension of virtual CPUs (vCPUs), and Ataru Runtime, a runtime system that manages the execution of an application defined by Directed Acyclic Graph (DAG) of functions and memory sharing within the virtual machine (VM). We evaluate Ataru against a process-based solution over Firecracker that offers similar VM isolation as Ataru, and show that Ataru outperforms Firecracker significantly in terms of bootup time, function execution time, and vCPU utilization, especially when the functions have execution times in the order of tens of microseconds.

Virtual machines (VMs) are a crucial technology for cloud computing, permitting multiple operating systems to run on a single physical host. Here, we propose a method for analyzing the performance of virtual machines in a cloud computing environment. The current approach of tracing both the host and virtual machines can be inefficient and may not be feasible for various reasons, such as security and privacy issues. We propose a host-only kernel tracing technique that uses only trace data generated on the host system. The trace data is then analyzed using the TraceCompass tool and two algorithms: Virtual CPU State Finder (VSF) and State Time Analysis (STA). The VSF algorithm generates a graphical view of the state of each thread running inside virtual machines for the identification of latency and performance degradation. The STA algorithm calculates the amount of time each virtual CPU spends in different states, providing important insights into the resource utilization and performance of virtual resources. In addition, our usage of the Trace Compass tool and EASE scripting allows more manageable analysis and visualization of the tracing data, making it accessible to a broader range of users. This method provides cloud providers with valuable information to maintain QoS and SLA parameters and improve the overall performance of running VMs.

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides *feedback* for its output and uses it to *refine* itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner and the feedback provider. We evaluate Self-Refine across 7 diverse tasks, ranging from dialog response generation to mathematical reasoning, using state-of-the-art (GPT-3.5, ChatGPT, and GPT-4) LLMs. Across all evaluated tasks, outputs generated with Self-Refine are preferred by humans and automatic metrics over those generated with the same LLM using conventional one-step generation, improving by $\sim$20\% absolute on average in task performance. Our work demonstrates that even state-of-the-art LLMs like GPT-4 can be further improved at test-time using our simple, standalone approach.

Fact-checking is an essential tool to mitigate the spread of misinformation and disinformation.We introduce the task of fact-checking in dialogue, which is a relatively unexplored area.We construct DIALFACT, a testing benchmark dataset of 22,245 annotated conversational claims, paired with pieces of evidence from Wikipedia.There are three sub-tasks in DIALFACT: 1) Verifiable claim detection task distinguishes whether a response carries verifiable factual information; 2) Evidence retrieval task retrieves the most relevant Wikipedia snippets as evidence; 3) Claim verification task predicts a dialogue response to be supported, refuted, or not enough information.We found that existing fact-checking models trained on non-dialogue data like FEVER (Thorne et al., 2018) fail to perform well on our task, and thus, we propose a simple yet data-efficient solution to effectively improve fact-checking performance in dialogue.We point out unique challenges in DIALFACT such as handling the colloquialisms, coreferences and retrieval ambiguities in the error analysis to shed light on future research in this direction 1 .Dialogue Context: I have family in Ireland!Have you ever been there?Evidence: Ireland is an island in the North Atlantic.Non-Verifiable Response: I haven't been but want to!Verifiable Supported Response: I haven't.It is an island in the north Atlantic right?Verifiable Refuted Response: I haven't been.Isn't it somewhere in north Pacific?Verifiable NEI Response: I haven't been.I heard it's the most popular tourist location in Europe!

Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zeroshot performance on unseen tasks.Dialogue is an especially interesting area in which to explore instruction tuning because dialogue systems perform multiple tasks related to language (e.g., natural language understanding and generation, domain-specific interaction), yet instruction tuning has not been systematically explored for dialogue-related tasks.We introduce INSTRUCTDIAL, an instruction tuning framework for dialogue, which consists of a repository of 48 diverse dialogue tasks in a unified text-to-text format created from 59 openly available dialogue datasets.We explore crosstask generalization ability on models tuned on INSTRUCTDIAL across diverse dialogue tasks.Our analysis reveals that INSTRUCTDIAL enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection, and even better performance in a few-shot setting.To ensure that models adhere to instructions, we introduce novel meta-tasks.We establish benchmark zero-shot and few-shot performance of models trained using the proposed framework on multiple dialogue tasks 1 .

In this paper problem of offline signature verification has been discussed with a novel high-performance convolution Siamese network. The paper proposes modifications in the already existing convolution Siamese network. The proposed method makes use of the Batch Normalization technique instead of Local Response Normalization to achieve better accuracy. The regularization factor has been added in the fully connected layers of the convolution neural network to deal with the problem of overfitting. Apart from this, a wide range of learning rates are provided during the training of the model and optimal one having the least validation loss is used. To evaluate the proposed changes and compare the results with the existing solution, our model is validated on three benchmarks datasets viz. CEDAR, BHSig260, and GPDS Synthetic Signature Corpus. The evaluation is done via two methods firstly by Test-Train validation and then by K-fold cross-validation (K = 5), to test the skill of our model. We show that the proposed modified Siamese network outperforms all the prior results for offline signature verification. One of the major advantages of our system is its capability of handling an unlimited number of new users which is the drawback of many research works done in the past.

Prakhar Gupta, Martin Jaggi. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, Sadao Kurohashi. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Bug tracking is one of the prominent activities during the maintenance phase of software development. The severity of the bug acts as a key indicator of its criticality and impact towards planning evolution and maintenance of various types of software products. This indicator measures how negatively the bug may affect the system functionality. This helps in determining how quickly the development teams need to address the bug for successful execution of the software system. Due to a large number of bugs reported every day, the developers find it really difficult to assign the severity level to bugs accurately. Assigning incorrect severity level results in delaying the bug resolution process. Thus automated systems were developed which will assign a severity level using various machine learning techniques. In this work, five different types of sentence embedding techniques have been applied on bugs description to convert the description comments to an n-dimensional vector. These computed vectors are used as an input of the software defect severity level prediction models and ensemble techniques like Bagging, Random Forest classifier, Extra Trees classifier, AdaBoost and Gradient Boosting have been used to train these models. We have also considered different variants of the Synthetic Minority Oversampling Technique (SMOTE) to handle the class imbalance problem as the considered datasets are not evenly distributed. The experimental results on six projects highlight that the usage of sentence embedding, ensemble techniques, and different variants of SMOTE techniques helps in improving the predictive ability of defect severity level prediction models.

Prakhar Gupta, Jeffrey Bigham, Yulia Tsvetkov, Amy Pavel. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multireference evaluation.Existing metrics have been shown to correlate poorly with human judgement, particularly in open-domain dialog.One alternative is to collect human annotations for evaluation, which can be expensive and time consuming.To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references.A series of experiments show that the use of multiple references results in improved correlation between several automatic metrics and human judgement for both the quality and the diversity of system output.

Matteo Pagliardini, Prakhar Gupta, Martin Jaggi. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

We introduce models for saliency prediction for mobile user interfaces. A mobile interface may include elements like buttons and text in addition to natural images which enable performing a variety of tasks. Saliency in natural images is a well studied topic. However, given the difference in what constitutes a mobile interface, and the usage context of these devices, we postulate that saliency prediction for mobile interface images requires a fresh approach. Mobile interface design involves operating on elements, the building blocks of the interface. We first collected eye-gaze data from mobile devices for a free viewing task. Using this data, we develop a novel autoencoder based multi-scale deep learning model that provides saliency prediction at the mobile interface element level. Compared to saliency prediction approaches developed for natural images, we show that our approach performs significantly better on a range of established metrics.

Recent advances in sensor technology and ubiquitous computing have sustained them as a better alternative for kids activity monitoring system. This paper presents a system that continuously monitors the proper pencil grip and writing activity of kid using accelerometer and pressure sensors. The system creates a labeled dataset for recognizing the correct location of pencil grip, holding direction of the pencil, and writing activity of kids. The system uses a supervised machine learning technique and labeled dataset for classifying whether a kid properly uses a pencil or not. In addition, a prototype system is developed and adequately tested on real-time user data. The prototype uses accelerometer and pressure sensors for extracting the writing activities. The system uses bluetooth low energy for wirelessly transferring the sensed data of writing activities to the parent and teachers. The system is suitable for kids due to its low cost, small size, and low-power consumption.