In recent years, numerous tasks have been proposed to encourage model to develop specified capability in understanding audio-visual scene, primarily categorized into temporal localization, spatial localization, spatio-temporal reasoning, and pixel-level understanding. Instead, human possesses a unified understanding ability for diversified tasks. Therefore, designing an audio-visual model with general capability to unify these tasks is of great value. However, simply joint training for all tasks can lead to interference due to the heterogeneity of audiovisual data and complex relationship among tasks. We argue that this problem can be solved through explicit cooperation among tasks. To achieve this goal, we propose a unified learning method which achieves explicit inter-task cooperation from both the perspectives of data and model thoroughly. Specifically, considering the labels of existing datasets are simple words, we carefully refine these datasets and construct an Audio-Visual Unified Instruction-tuning dataset with Explicit reasoning process (AV-UIE), which clarifies the cooperative relationship among tasks. Subsequently, to facilitate concrete cooperation in learning stage, an interaction-aware LoRA structure with multiple LoRA heads is designed to learn different aspects of audiovisual data interaction. By unifying the explicit cooperation across the data and model aspect, our method not only surpasses existing unified audio-visual model on multiple tasks, but also outperforms most specialized models for certain tasks. Furthermore, we also visualize the process of explicit cooperation and surprisingly find that each LoRA head has certain audio-visual understanding ability. Code and dataset: https://github.com/GeWu-Lab/Crab
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software. The technologies of interacting with data particularly have an important entanglement with LLMs as efficient and intuitive data interactions are paramount. In this paper, we present DB-GPT, a revolutionary and product-ready Python library that integrates LLMs into traditional data interaction tasks to enhance user experience and accessibility. DB-GPT is designed to understand data interaction tasks described by natural language and provide context-aware responses powered by LLMs, making it an indispensable tool for users ranging from novice to expert. Its system design supports deployment across local, distributed, and cloud environments. Beyond handling basic data interaction tasks like Text-to-SQL with LLMs, it can handle complex tasks like generative data analysis through a Multi-Agents framework and the Agentic Workflow Expression Language (AWEL). The Service-oriented Multi-model Management Framework (SMMF) ensures data privacy and security, enabling users to employ DB-GPT with private LLMs. Additionally, DB-GPT offers a series of product-ready features designed to enable users to integrate DB-GPT within their product environments easily. The code of DB-GPT is available at Github(https://github.com/eosphoros-ai/DB-GPT) which already has over 10.7k stars. Please install DB-GPT for your own usage with the instructions(https://github.com/eosphoros-ai/DB-GPT#install) and watch a 5-minute introduction video on Youtube(https://youtu.be/n_8RI1ENyl4) to further investigate DB-GPT.
In this work, we present a comprehensive study of Meta Prompting (MP), an innovative technique reshaping the utilization of language models (LMs) and AI systems in problem-solving and data interaction. Grounded in type theory and category theory, Meta Prompting emphasizes the structure and syntax of information over traditional content-centric methods. The paper explores the formal definitions of Meta Prompting, sets it apart from few-shot prompting, and underlines its effectiveness in various AI applications. A key focus is applying Meta Prompting for complex reasoning tasks, showing how it effectively deconstructs intricate problems into simpler sub-problems, enhancing token efficiency, and enabling more equitable problem-solving comparisons, especially against few-shot prompting methods. Additionally, the paper introduces Meta Prompting for prompting tasks, allowing LLMs to self-generate new prompts in a recursive, metaprogramming-like manner. Empirical experiments, including using a Qwen-72B base language model equipped with meta prompt without instruction-tuning to solve MATH problems with accuracy at 46.3%, which surpass the supervised fine-tuned counterpart trained with extensive mathematical QA instruction pairs and even the initial version of GPT-4, solving GSM8K problems with 83.5% accuracy with zero-shot meta-prompted Qwen-72B base language model, and solving the Game of 24 tasks with a 100% success rate using GPT-4, demonstrate the meta prompting's efficacy in achieving high accuracy and efficiency, showcasing Meta Prompting's transformative impact on AI problem-solving The code is available at https://github.com/meta-prompting/meta-prompting.
Recent deep learning methods have led to increased interest in solving high-efficiency end-to-end transmission problems. These methods, we call nonlinear transform source-channel coding (NTSCC), extract the semantic latent features of source signal, and learn entropy model to guide the joint source-channel coding with variable rate to transmit latent features over wireless channels. In this paper, we propose a comprehensive framework for improving NTSCC, thereby higher system coding gain, better model versatility, and more flexible adaptation strategy aligned with semantic guidance are all achieved. This new sophisticated NTSCC model is now ready to support large-size data interaction in emerging XR, which catalyzes the application of semantic communications. Specifically, we propose three useful improvement approaches. First, we introduce a contextual entropy model to better capture the spatial correlations among the semantic latent features, thereby more accurate rate allocation and contextual joint source-channel coding are developed accordingly to enable higher coding gain. On that basis, we further propose response network architectures to formulate versatile NTSCC, i.e., once-trained model supports various rates and channel states that benefits the practical deployment. Following this, we propose an online latent feature editing method to enable more flexible coding rate control aligned with some specific semantic guidance. By comprehensively applying the above three improvement methods for NTSCC, a deployment-friendly semantic coded transmission system stands out finally. Our improved NTSCC system has been experimentally verified to achieve considerable bandwidth saving versus the state-of-the-art engineered VTM + 5G LDPC coded transmission system with lower processing latency.
The visual analytics community has proposed several user modeling algorithms to capture and analyze users' interaction behavior in order to assist users in data exploration and insight generation. For example, some can detect exploration biases while others can predict data points that the user will interact with before that interaction occurs. Researchers believe this collection of algorithms can help create more intelligent visual analytics tools. However, the community lacks a rigorous evaluation and comparison of these existing techniques. As a result, there is limited guidance on which method to use and when. Our paper seeks to fill in this missing gap by comparing and ranking eight user modeling algorithms based on their performance on a diverse set of four user study datasets. We analyze exploration bias detection, data interaction prediction, and algorithmic complexity, among other measures. Based on our findings, we highlight open challenges and new directions for analyzing user interactions and visualization provenance.
Virtual reality (VR) offers immersive visualization and intuitive interaction. We leverage VR to enable any biomedical professional to deploy a deep learning (DL) model for image classification. While DL models can be powerful tools for data analysis, they are also challenging to understand and develop. To make deep learning more accessible and intuitive, we have built a virtual reality-based DL development environment. Within our environment, the user can move tangible objects to construct a neural network only using their hands. Our software automatically translates these configurations into a trainable model and then reports its resulting accuracy on a test dataset in real-time. Furthermore, we have enriched the virtual objects with visualizations of the model's components such that users can achieve insight about the DL models that they are developing. With this approach, we bridge the gap between professionals in different fields of expertise while offering a novel perspective for model analysis and data interaction. We further suggest that techniques of development and visualization in deep learning can benefit by integrating virtual reality.