Humans possess the capability to comprehend diverse modalities and seamlessly transfer information between them. In this work, we introduce ModaVerse, a Multi-modal Large Language Model (MLLM) capable of comprehending and transforming content across various modalities including images, videos, and audio. Predominant MLLM frameworks have largely relied on the alignment of latent spaces of textual and non-textual features. This alignment process, which synchronizes a language model trained on textual data with encoders and decoders trained on multi-modal data, often necessitates extensive training of several projection layers in multiple stages. Inspired by LLM-as-agent methodologies, we propose a novel Input/Output (I/O) alignment mechanism that operates directly at the level of natural language. It aligns the LLM's output with the input of generative models, avoiding the complexities associated with latent feature alignments, and simplifying the multiple training stages of existing MLLMs into a single, efficient process. This conceptual advancement leads to significant reductions in both data and computational costs. By conducting experiments on several benchmarks, we demonstrate that our approach attains comparable performance with the state of the art while achieving considerable efficiencies in data usage and training duration.
AI algorithms at the edge demand smaller model sizes and lower computational complexity. To achieve these objectives, we adopt a green learning (GL) paradigm rather than the deep learning paradigm. GL has three modules: 1) unsupervised representation learning, 2) supervised feature learning, and 3) supervised decision learning. We focus on the second module in this work. In particular, we derive new discriminant features from proper linear combinations of input features, denoted by x, obtained in the first module. They are called complementary and raw features, respectively. Along this line, we present a novel supervised learning method to generate highly discriminant complementary features based on the least-squares normal transform (LNT). LNT consists of two steps. First, we convert a C-class classification problem to a binary classification problem. The two classes are assigned with 0 and 1, respectively. Next, we formulate a least-squares regression problem from the N-dimensional (N-D) feature space to the 1-D output space, and solve the least-squares normal equation to obtain one N-D normal vector, denoted by a1. Since one normal vector is yielded by one binary split, we can obtain M normal vectors with M splits. Then, Ax is called an LNT of x, where transform matrix A in R^{M by N} by stacking aj^T, j=1, ..., M, and the LNT, Ax, can generate M new features. The newly generated complementary features are shown to be more discriminant than the raw features. Experiments show that the classification performance can be improved by these new features.
We propose a new synthesis algorithm that can efficiently search programs with local variables (e.g., those introduced by lambdas). Prior bottom-up synthesis algorithms are not able to evaluate programs with free local variables, and therefore cannot effectively reduce the search space of such programs (e.g., using standard observational equivalence reduction techniques), making synthesis slow. Our algorithm can reduce the space of programs with local variables. The key idea, dubbed lifted interpretation, is to lift up the program interpretation process, from evaluating one program at a time to simultaneously evaluating all programs from a grammar. Lifted interpretation provides a mechanism to systematically enumerate all binding contexts for local variables, thereby enabling us to evaluate and reduce the space of programs with local variables. Our ideas are instantiated in the domain of web automation. The resulting tool, Arborist, can automate a significantly broader range of challenging tasks more efficiently than state-of-the-art techniques including WebRobot and Helena.
Table of contents (ToC) extraction centres on structuring documents in a hierarchical manner. In this paper, we propose a new dataset, ESGDoc, comprising 1,093 ESG annual reports from 563 companies spanning from 2001 to 2022. These reports pose significant challenges due to their diverse structures and extensive length. To address these challenges, we propose a new framework for Toc extraction, consisting of three steps: (1) Constructing an initial tree of text blocks based on reading order and font sizes; (2) Modelling each tree node (or text block) independently by considering its contextual information captured in node-centric subtree; (3) Modifying the original tree by taking appropriate action on each tree node (Keep, Delete, or Move). This construction-modelling-modification (CMM) process offers several benefits. It eliminates the need for pairwise modelling of section headings as in previous approaches, making document segmentation practically feasible. By incorporating structured information, each section heading can leverage both local and long-distance context relevant to itself. Experimental results show that our approach outperforms the previous state-of-the-art baseline with a fraction of running time. Our framework proves its scalability by effectively handling documents of any length.
Remote sensing anomaly detector can find the objects deviating from the background as potential targets. Given the diversity in earth anomaly types, a unified anomaly detector across modalities and scenes should be cost-effective and flexible to new earth observation sources and anomaly types. However, the current anomaly detectors are limited to a single modality and single scene, since they aim to learn the varying background distribution. Motivated by the universal anomaly deviation pattern, in that anomalies exhibit deviations from their local context, we exploit this characteristic to build a unified anomaly detector. Firstly, we reformulate the anomaly detection task as an undirected bilayer graph based on the deviation relationship, where the anomaly score is modeled as the conditional probability, given the pattern of the background and normal objects. The learning objective is then expressed as a conditional probability ranking problem. Furthermore, we design an instantiation of the reformulation in the data, architecture, and optimization aspects. Simulated spectral and spatial anomalies drive the instantiated architecture. The model is optimized directly for the conditional probability ranking. The proposed model was validated in five modalities including the hyperspectral, visible light, synthetic aperture radar (SAR), infrared and low light to show its unified detection ability.
Large Language Models (LLMs), primarily trained on text-based datasets, exhibit exceptional proficiencies in understanding and executing complex linguistic instructions via text outputs. However, they falter when requests to generate non-text ones. Concurrently, modality conversion models, such as text-to-image, despite generating high-quality images, suffer from a lack of extensive textual pretraining. As a result, these models are only capable of accommodating specific image descriptions rather than comprehending more complex instructions. To bridge this gap, we propose a novel approach, \methodname, from a modality conversion perspective that evolves a text-based LLM into a multi-modal one. We specifically employ a minimal dataset to instruct LLMs to recognize the intended output modality as directed by the instructions. Consequently, the adapted LLM can effectively summon various off-the-shelf modality conversion models from the model zoos to generate non-text responses. This circumvents the necessity for complicated pretraining that typically requires immense quantities of paired multi-modal data, while simultaneously inheriting the extensive knowledge of LLMs and the ability of high-quality generative models. To evaluate and compare the adapted multi-modal LLM with its traditional counterparts, we have constructed a multi-modal instruction benchmark that solicits diverse modality outputs. The experiment results reveal that, with minimal training, LLMs can be conveniently adapted to comprehend requests for non-text responses, thus achieving higher flexibility in multi-modal scenarios. Code and data will be made available at https://github.com/xinke-wang/SwitchGPT.
Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data, which has broad prospects in various earth vision applications. However, when PU learning meets limited labeled HSI, the unlabeled data may dominate the optimization process, which makes the neural networks overfit the unlabeled data. In this paper, a Taylor variational loss is proposed for HSI PU learning, which reduces the weight of the gradient of the unlabeled data by Taylor series expansion to enable the network to find a balance between overfitting and underfitting. In addition, the self-calibrated optimization strategy is designed to stabilize the training process. Experiments on 7 benchmark datasets (21 tasks in total) validate the effectiveness of the proposed method. Code is at: https://github.com/Hengwei-Zhao96/T-HOneCls.
Knowledge workers frequently encounter repetitive web data entry tasks, like updating records or placing orders. Web automation increases productivity, but translating tasks to web actions accurately and extending to new specifications is challenging. Existing tools can automate tasks that perform the same logical trace of UI actions (e.g., input text in each field in order), but do not support tasks requiring different executions based on varied input conditions. We present DiLogics, a programming-by-demonstration system that utilizes NLP to assist users in creating web automation programs that handle diverse specifications. DiLogics first semantically segments input data to structured task steps. By recording user demonstrations for each step, DiLogics generalizes the web macros to novel but semantically similar task requirements. Our evaluation showed that non-experts can effectively use DiLogics to create automation programs that fulfill diverse input instructions. DiLogics provides an efficient, intuitive, and expressive method for developing web automation programs satisfying diverse specifications.
In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities. However, the intricate command structure and high learning curve create a barrier, particularly for novice printed circuit board (PCB) designers. This results in difficulties in selecting appropriate functions or plugins for varying design purposes, compounded by the lack of intuitive learning methods beyond traditional documentation, videos, and online forums. To address this challenge, an artificial intelligence (AI) interaction assist plugin for EDA software named SmartonAl is developed here, also KiCad is taken as the first example. SmartonAI is inspired by the HuggingGPT framework and employs large language models, such as GPT and BERT, to facilitate task planning and execution. On receiving a designer request, SmartonAI conducts a task breakdown and efficiently executes relevant subtasks, such as analysis of help documentation paragraphs and execution of different plugins, along with leveraging the built-in schematic and PCB manipulation functions in both SmartonAl itself and software. Our preliminary results demonstrate that SmartonAI can significantly streamline the PCB design process by simplifying complex commands into intuitive language-based interactions. By harnessing the powerful language capabilities of ChatGPT and the rich design functions of KiCad, the plugin effectively bridges the gap between complex EDA software and user-friendly interaction. Meanwhile, the new paradigm behind SmartonAI can also extend to other complex software systems, illustrating the immense potential of AI-assisted user interfaces in advancing digital interactions across various domains.