Information-seeking conversation, which aims to help users gather information through conversation, has achieved great progress in recent years. However, the research is still stymied by the scarcity of training data. To alleviate this problem, we propose AutoConv for synthetic conversation generation, which takes advantage of the few-shot learning ability and generation capacity of large language models (LLM). Specifically, we formulate the conversation generation problem as a language modeling task, then finetune an LLM with a few human conversations to capture the characteristics of the information-seeking process and use it for generating synthetic conversations with high quality. Experimental results on two frequently-used datasets verify that AutoConv has substantial improvements over strong baselines and alleviates the dependence on human annotation. In addition, we also provide several analysis studies to promote future research.
相關內容
Large Language Models (LLMs) have shown promise in the autonomous driving sector, particularly in generalization and interpretability. We introduce a unique object-level multimodal LLM architecture that merges vectorized numeric modalities with a pre-trained LLM to improve context understanding in driving situations. We also present a new dataset of 160k QA pairs derived from 10k driving scenarios, paired with high quality control commands collected with RL agent and question answer pairs generated by teacher LLM (GPT-3.5). A distinct pretraining strategy is devised to align numeric vector modalities with static LLM representations using vector captioning language data. We also introduce an evaluation metric for Driving QA and demonstrate our LLM-driver's proficiency in interpreting driving scenarios, answering questions, and decision-making. Our findings highlight the potential of LLM-based driving action generation in comparison to traditional behavioral cloning. We make our benchmark, datasets, and model available for further exploration.
Deployment of robotic systems in the real world requires a certain level of robustness in order to deal with uncertainty factors, such as mismatches in the dynamics model, noise in sensor readings, and communication delays. Some approaches tackle these issues reactively at the control stage. However, regardless of the controller, online motion execution can only be as robust as the system capabilities allow at any given state. This is why it is important to have good motion plans to begin with, where robustness is considered proactively. To this end, we propose a metric (derived from first principles) for representing robustness against external disturbances. We then use this metric within our trajectory optimization framework for solving complex loco-manipulation tasks. Through our experiments, we show that trajectories generated using our approach can resist a greater range of forces originating from any possible direction. By using our method, we can compute trajectories that solve tasks as effectively as before, with the added benefit of being able to counteract stronger disturbances in worst-case scenarios.
Unfamiliar decisions -- decisions where people lack adequate domain knowledge or expertise -- specifically increase the complexity and uncertainty of the process of searching for, understanding, and making decisions with online information. Through our formative study (n=14), we observed users' challenges in accessing diverse perspectives, identifying relevant information, and deciding the right moment to make the final decision. We present ChoiceMates, a system that enables conversations with a dynamic set of LLM-powered agents for a holistic domain understanding and efficient discovery and management of information to make decisions. Agents, as opinionated personas, flexibly join the conversation, not only providing responses but also conversing among themselves to elicit each agent's preferences. Our between-subjects study (n=36) comparing ChoiceMates to conventional web search and single-agent showed that ChoiceMates was more helpful in discovering, diving deeper, and managing information compared to Web with higher confidence. We also describe how participants utilized multi-agent conversations in their decision-making process.
We present CGAAL, our efficient on-the-fly model checker for alternating-time temporal logic (ATL) on concurrent game structures (CGS). We present how our tool encodes ATL as extended dependency graphs with negation edges and employs the distributed on-the-fly algorithm by Dalsgaard et al. Our tool offers multiple novel search strategies for the algorithm, including DHS which is inspired by PageRank and uses the in-degree of configurations as a heuristic, IHS which estimates instability of assignment values, and LPS which estimates the distance to a state satisfying the constituent property using linear programming. CGS are input using our modelling language LCGS, where composition and synchronisation are easily described. We prove the correctness of our encoding, and our experiments show that our tool CGAAL is often one to three orders of magnitude faster than the popular tool PRISM-games on case studies from PRISM's documentation and among case studies we have developed. In our evaluation, we also compare and evaluate our search strategies, and find that our custom search strategies are often significantly faster than the usual breadth-first and depth-first search strategies.
As the workforce settles into flexible work arrangements, researchers have focused on the collaborative and psychological consequences of the shift. While nearly a fifth of the world's population is estimated to be neurodivergent, the implications of remote collaboration on the cognitive, sensory, and socio-affective experiences of autistic workers are poorly understood. Prior literature suggests that information and communication technologies (ICTs) introduce major psychological stressors. Theoretically, these stressors ought to be exceptionally straining considering autistic traits $\unicode{x2013}$ yet, studies describe a strong attraction to ICTs. We thus ask: how do digital technologies alleviate autistic workers' experiences of their collaborative work environment? Thirty-three interviews were conducted to address this question. Findings suggest that digital media present capabilities that filter input from the environment, turning it into a virtual stage that lets workers "time out". The resulting "technorelief" enables autistic workers to tune into their perceptions and regain control of their collaborative experiences.
This paper addresses the multi-faceted problem of robot grasping, where multiple criteria may conflict and differ in importance. We introduce Grasp Ranking and Criteria Evaluation (GRaCE), a novel approach that employs hierarchical rule-based logic and a rank-preserving utility function to optimize grasps based on various criteria such as stability, kinematic constraints, and goal-oriented functionalities. Additionally, we propose GRaCE-OPT, a hybrid optimization strategy that combines gradient-based and gradient-free methods to effectively navigate the complex, non-convex utility function. Experimental results in both simulated and real-world scenarios show that GRaCE requires fewer samples to achieve comparable or superior performance relative to existing methods. The modular architecture of GRaCE allows for easy customization and adaptation to specific application needs.
Recently, APT attacks have frequently happened, which are increasingly complicated and more challenging for traditional security detection models. The system logs are vital for cyber security analysis mainly due to their effective reconstruction ability of system behavior. existing log collection tools built on ETW for Windows suffer from working shortages, including data loss, high overhead, and weak real-time performance. Therefore, It is still very difficult to apply ETW-based Windows tools to analyze APT attack scenarios. To address these challenges, this paper proposes an efficient and lossless kernel log collector called Kellect, which has open sourced with project at www.kellect.org. It takes extra CPU usage with only 2%-3% and about 40MB memory consumption, by dynamically optimizing the number of cache and processing threads through a multi-level cache solution. By replacing the TDH library with a sliding pointer, Kellect enhances analysis performance, achieving at least 9 times the efficiency of existing tools. Furthermore, Kellect improves compatibility with different OS versions. Additionally, Kellect enhances log semantics understanding by maintaining event mappings and application callstacks which provide more comprehensive characteristics for security behavior analysis. With plenty of experiments, Kellect demonstrates its capability to achieve non-destructive, real-time and full collection of kernel log data generated from events with a comprehensive efficiency of 9 times greater than existing tools. As a killer illustration to show how Kellect can work for APT, full data logs have been collected as a dataset Kellect4APT, generated by implementing TTPs from the latest ATT&CK. To our knowledge, it is the first open benchmark dataset representing ATT&CK technique-specific behaviors, which could be highly expected to improve more extensive research on APT study.
While recent research has made significant progress in speech-driven talking face generation, the quality of the generated video still lags behind that of real recordings. One reason for this is the use of handcrafted intermediate representations like facial landmarks and 3DMM coefficients, which are designed based on human knowledge and are insufficient to precisely describe facial movements. Additionally, these methods require an external pretrained model for extracting these representations, whose performance sets an upper bound on talking face generation. To address these limitations, we propose a novel method called DAE-Talker that leverages data-driven latent representations obtained from a diffusion autoencoder (DAE). DAE contains an image encoder that encodes an image into a latent vector and a DDIM image decoder that reconstructs the image from it. We train our DAE on talking face video frames and then extract their latent representations as the training target for a Conformer-based speech2latent model. This allows DAE-Talker to synthesize full video frames and produce natural head movements that align with the content of speech, rather than relying on a predetermined head pose from a template video. We also introduce pose modelling in speech2latent for pose controllability. Additionally, we propose a novel method for generating continuous video frames with the DDIM image decoder trained on individual frames, eliminating the need for modelling the joint distribution of consecutive frames directly. Our experiments show that DAE-Talker outperforms existing popular methods in lip-sync, video fidelity, and pose naturalness. We also conduct ablation studies to analyze the effectiveness of the proposed techniques and demonstrate the pose controllability of DAE-Talker.
Many have criticized the centralized and unaccountable governance of prominent online social platforms, leading to renewed interest in platform governance that incorporates multiple centers of power. Decentralization of power can arise horizontally, through parallel communities, each with local administration, and vertically, through multiple hierarchies of overlapping jurisdiction. Drawing from literature on federalism and polycentricity in analogous offline institutions, we scrutinize the landscape of existing platforms through the lens of multi-level governance. Our analysis describes how online platforms incorporate varying forms and degrees of decentralized governance. In particular, we propose a framework that characterizes the general design space and the various ways that middle levels of governance vary in how they can interact with a centralized governance system above and end users below. This focus provides a starting point for new lines of inquiry between platform- and community-governance scholarship. By engaging themes of decentralization, hierarchy, power, and responsibility, while discussing concrete examples, we connect designers and theorists of online spaces.
Following unprecedented success on the natural language tasks, Transformers have been successfully applied to several computer vision problems, achieving state-of-the-art results and prompting researchers to reconsider the supremacy of convolutional neural networks (CNNs) as {de facto} operators. Capitalizing on these advances in computer vision, the medical imaging field has also witnessed growing interest for Transformers that can capture global context compared to CNNs with local receptive fields. Inspired from this transition, in this survey, we attempt to provide a comprehensive review of the applications of Transformers in medical imaging covering various aspects, ranging from recently proposed architectural designs to unsolved issues. Specifically, we survey the use of Transformers in medical image segmentation, detection, classification, reconstruction, synthesis, registration, clinical report generation, and other tasks. In particular, for each of these applications, we develop taxonomy, identify application-specific challenges as well as provide insights to solve them, and highlight recent trends. Further, we provide a critical discussion of the field's current state as a whole, including the identification of key challenges, open problems, and outlining promising future directions. We hope this survey will ignite further interest in the community and provide researchers with an up-to-date reference regarding applications of Transformer models in medical imaging. Finally, to cope with the rapid development in this field, we intend to regularly update the relevant latest papers and their open-source implementations at \url{//github.com/fahadshamshad/awesome-transformers-in-medical-imaging}.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191