Data is one of the most critical elements in building a large language model. However, existing systems either fail to customize a corpus curation pipeline or neglect to leverage comprehensive corpus assessment for iterative optimization of the curation. To this end, we present a pretraining corpus curation and assessment platform called Oasis — a one-stop system for data quality improvement and quantification with user-friendly interactive interfaces. Specifically, the interactive modular rule filter module can devise customized rules according to explicit feedback. The debiased neural filter module builds the quality classification dataset in a negative-centric manner to remove the undesired bias. The adaptive document deduplication module could execute large-scale deduplication with limited memory resources. These three parts constitute the customized data curation module. And in the holistic data assessment module, a corpus can be assessed in local and global views, with three evaluation means including human, GPT-4, and heuristic metrics. We exhibit a complete process to use Oasis for the curation and assessment of pretraining data. In addition, an 800GB bilingual corpus curated by Oasis is publicly released.
论文检索
输入标题、作者或关键词，从 1,048 篇学术成果中精准定位
Reinforcement learning, optimization, and planning/search are interconnected domains in artificial intelligence. Algorithms within these domains share many similarities. They complement each other in solving complex decision-making problems, and also offer opportunities for cross-disciplinary integration. However, conducting research on algorithms across these domains typically requires learning the specialized libraries. These libraries often couple algorithms with domain-specific problem classes, making it difficult to conduct cross-disciplinary researches. In order to solve this problem, we developed a generic and lightweight framework for reinforcement learning, optimization, and planning/search algorithms (RLOP). It implements only the core logic of algorithms, abstracting away domain-specific details by defining interface functions, which enables flexible customization and efficient integration across different domains. The framework has been open-sourced at https://github.com/songzhg/RLOP.
Distributed deep reinforcement learning (DDRL) has gained increasing attention due to the emerging requirements for addressing complex games like Go and StarCraft. However, how to effectively and stably train bots with asynchronous and heterogeneous agents cooperation and competition for multiple players under multiple machines (with multiple CPUs and GPUs) using DDRL is still an open problem. We propose and open M2RL, a Multi-player and Multi-agent Reinforcement Learning framework, to make training bots for complex games an easy-to-use warehouse. Experiments involving training a two-player multi-agent Wargame AI, and a sixteen-player multi-agent community game Neural MMO AI, demonstrate the effectiveness of the proposed framework by winning a silver award and beating high-level AI bots designed by professional players.
While traditional search systems have mostly been satisfactorily relying on lexical based sparse retrievers such as BM25, recent research advances in neural models, the current day large language models (LLMs) hold good promise for practical search applications as well. In this work, we discuss a collaboration between IBM and National Library of Australia to upgrade an existing search application (referred to as NLA) over terabytes of Australian Web Archive data and serving thousands of daily users. We posit and demonstrate both empirically and through qualitative user studies that LLMs and neural models can indeed provide good gains, when combined effectively with traditional search. We believe this demonstration will show the unique challenges associated with real world practical deployments and also offer valuable insights into how to effectively upgrade legacy search applications in the era of LLMs.
Equipped with Denoising Diffusion Probabilistic Models, video content generation has gained significant research interest recently. However, diffusion pipelines call for intensive computation and model storage, which poses challenges for their wide and efficient deployment. In this work, we address this issue by integrating LCM-LoRA to reduce the denoising steps and escalating the video generation process by frame skipping and interpolation. Our framework achieves an approximately 10× inference acceleration for high-quality realistic video generation on commonly available GPUs.
Reinforcement Learning for Athletic Intelligence: Lessons from the 1st “AI Olympics with RealAIGym” Competition
PDF ↗As artificial intelligence gains new capabilities, it becomes important to evaluate it on real-world tasks. In particular, the fields of robotics and reinforcement learning (RL) are lacking in standardized benchmarking tasks on real hardware. To facilitate reproducibility and stimulate algorithmic advancements, we held an AI Olympics competition at IJCAI 2023 conference based on the double pendulum system in the RealAIGym project where the participants were asked to develop a controller for the swing up and stabilization task. This paper presents the methods and results from the top participating teams and provides insights into the real-world performance of RL algorithms with respect to a baseline time-varying LQR controller.
In recent years, badminton analytics has drawn attention due to the advancement of artificial intelligence and the efficiency of data collection. While there is a line of effective applications to improve and investigate player performance, there are only a few public badminton datasets that can be used by researchers outside the badminton domain. Existing badminton singles datasets focus on specific matchups; however, they cannot provide comprehensive studies on different players and various matchups. In this paper, we provide a badminton singles dataset, ShuttleSet22, which is collected from high-ranking matches in 2022. ShuttleSet22 consists of 30,172 strokes in 2,888 rallies in the training set, 1,400 strokes in 450 rallies in the validation set, and 2,040 strokes in 654 rallies in the testing set, with detailed stroke-level metadata within a rally. To benchmark existing work with ShuttleSet22, we hold a challenge, Track 2: Forecasting Future Turn-Based Strokes in Badminton Rallies, at CoachAI Badminton Challenge @ IJCAI 2023, to encourage researchers to tackle this real-world problem through innovative approaches and to summarize insights between the state-of-the-art baseline and improved techniques, exchanging inspiring ideas. The baseline codes and the dataset are made available at https://github.com/wywyWang/CoachAI-Projects/tree/main/CoachAI-Challenge-IJCAI2023.
A carbon market is a market-based tool that incentivizes economic agents to align individual profits with the global utility, i.e., reducing carbon emissions to tackle climate change. Cap and trade stands as a critical principle based on allocating and trading carbon allowances (carbon emission credit), enabling economic agents to follow planned emissions and penalizing excess emissions. A central authority is responsible for introducing and allocating those allowances in cap and trade. However, the complexity of carbon market dynamics makes accurate simulation intractable, which in turn hinders the design of effective allocation strategies. To address this, we propose an adaptive mechanism design framework, simulating the market using hierarchical, model-free multi-agent reinforcement learning (MARL). Government agents allocate carbon credits, while enterprises engage in economic activities and carbon trading. This framework illustrates agents’ behavior comprehensively. Numerical results show MARL enables government agents to balance productivity, equality, and carbon emissions. Our project is available at https: //anonymous.4open.science/r/Carbon-Simulator.
Between 2021 and 2023, AI-Olympics---a series of online AI competitions, was hosted by the online evaluation platform Jidi in collaboration with the IJCAI committee. In these competitions, an agent is required to accomplish diverse sports tasks in a two-dimensional continuous world, while competing against an opponent. This paper provides a brief overview of the competition series and highlights notable findings. We aim to contribute insights to the field of multi-agent decision-making and explore the generalization of agents through engineering efforts.
This paper describes the KnowledgeHub tool, a scientific literature Information Extraction (IE) and Question Answering (QA) pipeline. This is achieved by supporting the ingestion of PDF documents that are converted to text and structured representations. An ontology can then be constructed where a user defines the types of entities and relationships they want to capture. A browser-based annotation tool enables annotating the contents of the PDF documents according to the ontology. Named Entity Recognition (NER) and Relation Classification (RC) models can be trained on the resulting annotations and can be used to annotate the unannotated portion of the documents. A knowledge graph is constructed from these entity and relation triples which can be queried to obtain insights from the data. Furthermore, we integrate a suite of Large Language Models (LLMs) that can be used for QA and summarisation that is grounded in the included documents. KnowledgeHub is a unique tool that supports annotation, IE and QA, which gives the user full insight into the knowledge discovery pipeline.
Dealing with the ever-increasing demand for traffic management is one of the main challenges of the 21st century. The issue is much more apparent in urban areas during rush hours. Traffic congestion causes economic losses due to delays and increased fuel consumption and, on top of that, is a major health risk. Intelligent centralized traffic routing is an important concept aiming at reducing traffic congestion in urban areas by more effectively utilizing road networks. In this demo, we present a framework that, in a nutshell, integrates techniques for intelligent centralized traffic routing into the well-known SUMO simulator, so these techniques can be evaluated in realistic settings on real/realistic datasets. In particular, the framework automatically identifies ``problematic'' urban regions by analyzing historical traffic data, then simplifies the road networks by precomputing promising routes (for each considered traffic flow), and finally, leverages a planning-based approach to generate routes. Our framework is evaluated on a real dataset from Dublin's metropolitan area.
Deep learning models have shown their strengths in various application domains, however, they often struggle to meet safety requirements for their outputs. In this paper, we introduce PiShield, the first package ever allowing for the integration of the requirements into the neural networks' topology. PiShield guarantees compliance with these requirements, regardless of input. Additionally, it allows for integrating requirements both at inference and/or training time, depending on the practitioners' needs. Given the widespread application of deep learning, there is a growing need for frameworks allowing for the integration of the requirements across various domains. Here, we explore three application scenarios: functional genomics, autonomous driving, and tabular data generation.
Attention has been a crucial component in the success of image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the importance of dense attention in generative image models, which often contain redundant features, making them suitable for sparser attention mechanisms. We propose a novel training-free method ToDo that relies on token downsampling of key and value tokens to accelerate Stable Diffusion inference by up to 2x for common sizes and up to 4.5x or more for high resolutions like 2048 × 2048. We demonstrate that our approach outperforms previous methods in balancing efficient throughput and fidelity.
Intelligent Process Automation (IPA) solutions must adapt to changes in user interfaces autonomously, without manual intervention. Addressing this critical challenge and aiming to advance the state-of-the-art, last year we introduced the IPA Challenge competition at IJCAI 2023. This demo paper presents IDA - our novel UI automation solution, developed to tackle complex resiliency issues. Leveraging the capabilities of large language models and employing grounded instructions, our system demonstrates a significant advancement towards resilient IPA. We provide an overview of the IPA Challenge, detail the architecture of our system, and illustrate its effectiveness in overcoming the resiliency challenges. A link to the demo video can be found at: https://youtu.be/G5nI3V9Umjc
We introduce O2ARC 3.0 interface for the Abstraction and Reasoning Corpus (ARC). O2ARC 3.0 gamifies the experience, fostering user engagement through competitive features and community-driven problem creation and evaluation. Built with a React frontend and NestJS backend, the platform provides a responsive and intuitive interface for efficient rule inference. This approach not only improves data collection for AI training but also enhances the problem-solving process, offering a scalable solution for advancing cognitive AI research. O2ARC is available at https://o2arc.com.
We present a new problem called rhythm inference. It consists in inferring the duration of each note and each rest from a partial specification. We then formulate rhythm inference as a constraint satisfaction problem and we use mixed linear programming to solve it. The solution is implemented for a language representing music scores, called abcd. Interestingly, the rhythm is inferred in real-time from partial musical indications.
In this paper, we introduce the novel technological framework for the development of emotional dialogue systems. Inspired by the "Inside Out" film, we propose to use multiple emotional agents based on Large Language Models (LLMs) to prepare answers to a user query. Their answers are aggregated into a single response, taking into account the current emotional state of a user. The latter is estimated by video-based facial expression recognition (FER). We introduce several publicly available lightweight neural networks that show near state-of-the-art results on the AffectNet dataset. Qualitative examples using either GPT-3.5 or LLama2 and Mistral demonstrate that the proposed approach leads to more emotional responses in LLMs.
We present a novel prompting strategy for artificial intelligence driven digital avatars. To better quantify how our prompting strategy affects anthropomorphic features like humor, authenticity, and favorability we present Crowd Vote - an adaptation of Crowd Score that allows for judges to elect a large language model (LLM) candidate over competitors answering the same or similar prompts. To visualize the responses of our LLM, and the effectiveness of our prompting strategy we propose an end-to-end framework for creating high-fidelity artificial intelligence (AI) driven digital avatars. This pipeline effectively captures an individual's essence for interaction and our streaming algorithm delivers a high-quality digital avatar with real-time audio-video streaming from server to mobile device. Both our visualization tool, and our Crowd Vote metrics demonstrate our AI driven digital avatars have state-of-the-art humor, authenticity, and favorability outperforming all competitors and baselines. In the case of our Donald Trump and Joe Biden avatars, their authenticity and favorability are rated higher than even their real-world equivalents.
The development of the smart manufacturing trend includes the integration of Artificial Intelligence technologies into industrial processes. One example of such implementation is deep learning models that diagnose the current state of a technological process. Recent studies have demonstrated that small data perturbations, named adversarial attacks, can significantly affect the correct predictions of such models. This fact is critical in industrial systems, where AI-based decisions can be made to manage physical equipment. In this work, we present a system which can help to evaluate the robustness of technological process diagnosis models to adversarial attacks, as well as consider protection options. We briefly review the system's modules and also consider some useful applications. Our demo video is available at: http://tinyurl.com/3by9zcj5
This research introduces XGA-Osteo, an innovative approach that leverages Explainable Artificial Intelligence (XAI) to enhance the accuracy and interpretability of knee osteoarthritis diagnosis. Recent studies have utilized AI approaches to automate the diagnosis using knee joint X-ray images. However, these studies have primarily focused on predicting the severity of osteoarthritis without providing additional information to assist doctors in their diagnoses. In addition to accurately diagnosing the severity of the condition, XGA-Osteo generates an anomaly map, produced from a reconstructed image of a healthy knee using adversarial learning. Thus, the abnormal regions in X-ray images can be highlighted, offering valuable supplementary information to medical experts during the diagnosis process.