This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations in a harmonious way. Instead of tuning parameters for each object, our model is trained only once and effortlessly generalizes to diverse object-scene combinations at the inference stage. Such a challenging zero-shot setting requires an adequate characterization of a certain object. To this end, we complement the commonly used identity feature with detail features, which are carefully designed to maintain texture details yet allow versatile local variations (e.g., lighting, orientation, posture, etc.), supporting the object in favorably blending with different surroundings. We further propose to borrow knowledge from video datasets, where we can observe various forms (i.e., along the time axis) of a single object, leading to stronger model generalizability and robustness. Extensive experiments demonstrate the superiority of our approach over existing alternatives as well as its great potential in real-world applications, such as virtual try-on and object moving. Project page is https://damo-vilab.github.io/AnyDoor-Page/.
In recent years, personality has been regarded as a valuable personal factor being incorporated into numerous tasks such as sentiment analysis and product recommendation. This has led to widespread attention to text-based personality recognition task, which aims to identify an individual's personality based on given text. Considering that ChatGPT has recently exhibited remarkable abilities on various natural language processing tasks, we provide a preliminary evaluation of ChatGPT on text-based personality recognition task for generating effective personality data. Concretely, we employ a variety of prompting strategies to explore ChatGPT's ability in recognizing personality from given text, especially the level-oriented prompting strategy we designed for guiding ChatGPT in analyzing given text at a specified level. We compare the performance of ChatGPT on two representative real-world datasets with traditional neural network, fine-tuned RoBERTa, and corresponding state-of-the-art task-specific model. The experimental results show that ChatGPT with zero-shot chain-of-thought prompting exhibits impressive personality recognition ability. Triggered by zero-shot chain-of-thought prompting, ChatGPT outperforms fine-tuned RoBERTa on the two datasets and is capable to provide natural language explanations through text-based logical reasoning. Furthermore, relative to zero-shot chain-of-thought prompting, zero-shot level-oriented chain-of-thought prompting enhances the personality prediction ability of ChatGPT and reduces the performance gap between ChatGPT and corresponding state-of-the-art task-specific model. Besides, we also conduct experiments to observe the fairness of ChatGPT when identifying personality and discover that ChatGPT shows unfairness to some sensitive demographic attributes such as gender and age.
Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era of artificial intelligence. Unlike traditional approaches that require labeled samples for training, AL iteratively selects unlabeled samples to be annotated by an expert. This protocol aims to prioritize the most informative samples, leading to improved model performance compared to training with all labeled samples. In recent years, AL has gained increasing attention, particularly in the field of physics. This paper presents a comprehensive and accessible introduction to the theory of AL reviewing the latest advancements across various domains. Additionally, we explore the potential integration of AL with quantum ML, envisioning a synergistic fusion of these two fields rather than viewing AL as a mere extension of classical ML into the quantum realm.
We show that any randomized first-order algorithm which minimizes a $d$-dimensional, $1$-Lipschitz convex function over the unit ball must either use $\Omega(d^{2-\delta})$ bits of memory or make $\Omega(d^{1+\delta/6-o(1)})$ queries, for any constant $\delta\in (0,1)$ and when the precision $\epsilon$ is quasipolynomially small in $d$. Our result implies that cutting plane methods, which use $\tilde{O}(d^2)$ bits of memory and $\tilde{O}(d)$ queries, are Pareto-optimal among randomized first-order algorithms, and quadratic memory is required to achieve optimal query complexity for convex optimization.
Decoding inner speech from the brain signal via hybridisation of fMRI and EEG data is explored to investigate the performance benefits over unimodal models. Two different bimodal fusion approaches are examined: concatenation of probability vectors output from unimodal fMRI and EEG machine learning models, and data fusion with feature engineering. Same task inner speech data are recorded from four participants, and different processing strategies are compared and contrasted to previously-employed hybridisation methods. Data across participants are discovered to encode different underlying structures, which results in varying decoding performances between subject-dependent fusion models. Decoding performance is demonstrated as improved when pursuing bimodal fMRI-EEG fusion strategies, if the data show underlying structure.
Data valuation -- quantifying the contribution of individual data sources to certain predictive behaviors of a model -- is of great importance to enhancing the transparency of machine learning and designing incentive systems for data sharing. Existing work has focused on evaluating data sources with the shared feature or sample space. How to valuate fragmented data sources of which each only contains partial features and samples remains an open question. We start by presenting a method to calculate the counterfactual of removing a fragment from the aggregated data matrix. Based on the counterfactual calculation, we further propose 2D-Shapley, a theoretical framework for fragmented data valuation that uniquely satisfies some appealing axioms in the fragmented data context. 2D-Shapley empowers a range of new use cases, such as selecting useful data fragments, providing interpretation for sample-wise data values, and fine-grained data issue diagnosis.
Magnetic Resonance Spectroscopy (MRS) is an important non-invasive technique for in vivo biomedical detection. However, it is still challenging to accurately quantify metabolites with proton MRS due to three problems: Serious overlaps of metabolite signals, signal distortions due to non-ideal acquisition conditions and interference with strong background signals including macromolecule signals. The most popular software, LCModel, adopts the non-linear least square to quantify metabolites and addresses these problems by introducing regularization terms, imperfection factors of non-ideal acquisition conditions, and designing several empirical priors such as basissets of both metabolites and macromolecules. However, solving such a large non-linear quantitative problem is complicated. Moreover, when the signal-to-noise ratio of an input MRS signal is low, the solution may have a large deviation. In this work, deep learning is introduced to reduce the complexity of solving this overall quantitative problem. Deep learning is designed to predict directly the imperfection factors and the overall signal from macromolecules. Then, the remaining part of the quantification problem becomes a much simpler effective fitting and is easily solved by Linear Least Squares (LLS), which greatly improves the generalization to unseen concentration of metabolites in the training data. Experimental results show that compared with LCModel, the proposed method has smaller quantification errors for 700 sets of simulated test data, and presents more stable quantification results for 20 sets of healthy in vivo data at a wide range of signal-to-noise ratio. Qnet also outperforms other deep learning methods in terms of lower quantification error on most metabolites. Finally, QNet has been deployed on a cloud computing platform, CloudBrain-MRS, which is open accessed at https://csrc.xmu.edu.cn/CloudBrain.html.
We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. We examine our system on Chinese $\rightarrow$ English and English $\rightarrow$ Spanish pairs. Experimental results show that our system can generate speech with high translation quality and audio quality. Speech samples are available at https://speechtranslation.github.io/polyvoice.
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.
We introduce CONA, a novel context-aware instruction paradigm for effective knowledge dissemination using generative pre-trained transformer (GPT) models. CONA is a flexible framework designed to leverage the capabilities of Large Language Models (LLMs) and incorporate DIKW (Data, Information, Knowledge, Wisdom) hierarchy to automatically instruct and optimise presentation content, anticipate potential audience inquiries, and provide context-aware answers that adaptive to the knowledge level of the audience group. The unique aspect of the CONA paradigm lies in its combination of an independent advisory mechanism and a recursive feedback loop rooted on the DIKW hierarchy. This synergy significantly enhances context-aware contents, ensuring they are accessible and easily comprehended by the audience. This paradigm is an early pioneer to explore new methods for knowledge dissemination and communication in the LLM era, offering effective support for everyday knowledge sharing scenarios. We conduct experiments on a range of audience roles, along with materials from various disciplines using GPT4. Both quantitative and qualitative results demonstrated that the proposed CONA paradigm achieved remarkable performance compared to the outputs guided by conventional prompt engineering.