This paper presents a Pronunciation-Aware Contextualized (PAC) framework to address two key challenges in Large Language Model (LLM)-based Automatic Speech Recognition (ASR) systems: effective pronunciation modeling and robust homophone discrimination. Both are essential for raw or long-tail word recognition. The proposed approach adopts a two-stage learning paradigm. First, we introduce a pronunciation-guided context learning method. It employs an interleaved grapheme-phoneme context modeling strategy that incorporates grapheme-only distractors, encouraging the model to leverage phonemic cues for accurate recognition. Then, we propose a pronunciation-discriminative reinforcement learning method with perturbed label sampling to further enhance the modelś ability to distinguish contextualized homophones. Experimental results on the public English Librispeech and Mandarin AISHELL-1 datasets indicate that PAC: (1) reduces relative Word Error Rate (WER) by 30.2% and 53.8% compared to pre-trained LLM-based ASR models, and (2) achieves 31.8% and 60.5% relative reductions in biased WER for long-tail words compared to strong baselines, respectively.

The believable simulation of multi-user behavior is crucial for understanding complex social systems. Recently, large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-like intelligence across various tasks. However, real human societies are often dynamic and complex, involving numerous individuals engaging in multimodal interactions. In this paper, taking e-commerce scenarios as an example, we present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs. In LMAgent, besides freely chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce. To simulate this complex system, we introduce a self-consistency prompting mechanism to augment agents' multimodal capabilities, resulting in significantly improved decision-making performance over the existing multi-agent system. Moreover, we propose a fast memory mechanism combined with the small-world model to enhance system efficiency, which supports more than 10,000 agent simulations in a society. Experiments on agents' behavior show that these agents achieve comparable performance to humans in behavioral indicators. Furthermore, compared with the existing LLMs-based multi-agent system, more different and valuable phenomena are exhibited, such as herd behavior, which demonstrates the potential of LMAgent in credible large-scale social behavior simulations.

Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers (ViTs) against adversarial perturbations. Tested on various white-box and transfer attack settings, we find that ViTs possess better adversarial robustness when compared with MLP-Mixer and convolutional neural networks (CNNs) including ConvNeXt, and this observation also holds for certified robustness. Through frequency analysis and feature visualization, we summarize the following main observations contributing to the improved robustness of ViTs: 1) Features learned by ViTs contain less high-frequency patterns that have spurious correlation, which helps explain why ViTs are less sensitive to high-frequency perturbations than CNNs and MLP-Mixer, and there is a high correlation between how much the model learns high-frequency features and its robustness against different frequency-based perturbations. 2) Introducing convolutional or tokens-to-token blocks for learning high-frequency features in ViTs can improve classification accuracy but at the cost of adversarial robustness. 3) Modern CNN designs that borrow techniques from ViTs including activation function, layer norm, larger kernel size to imitate the global attention, and patchify the images as inputs, etc., could help bridge the performance gap between ViTs and CNNs not only in terms of performance, but also certified and empirical adversarial robustness. Moreover, we show adversarial training is also applicable to ViT for training robust models, and sharpness-aware minimization can also help improve robustness, while pre-training with clean images on larger datasets does not significantly improve adversarial robustness.

Document-level relation extraction (RE) poses new challenges compared to its sentence-level counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document associated with multiple possible relations. In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multi-label and multi-entity problems. The adaptive thresholding replaces the global threshold for multi-label classification in the prior work with a learnable entities-dependent threshold. The localized context pooling directly transfers attention from pre-trained language models to locate relevant context that is useful to decide the relation. We experiment on three document-level RE benchmark datasets: DocRED, a recently released large-scale RE dataset, and two datasets CDRand GDA in the biomedical domain. Our ATLOP (Adaptive Thresholding and Localized cOntext Pooling) model achieves an F1 score of 63.4, and also significantly outperforms existing models on both CDR and GDA.

In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained interplay between vision and language, and makes image-text matching more interpretable. Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less interpretable. In this paper, we present Stacked Cross Attention to discover the full latent alignments using both image regions and words in a sentence as context and infer image-text similarity. Our approach achieves the state-of-the-art results on the MS-COCO and Flickr30K datasets. On Flickr30K, our approach outperforms the current best methods by 22.1% relatively in text retrieval from image query, and 18.2% relatively in image retrieval with text query (based on Recall@1). On MS-COCO, our approach improves sentence retrieval by 17.8% relatively and image retrieval by 16.6% relatively (based on Recall@1 using the 5K test set). Code has been made available at: this https URL.

Existing works about fashion outfit compatibility focus on predicting the overall compatibility of a set of fashion items with their information from different modalities. However, there are few works explore how to explain the prediction, which limits the persuasiveness and effectiveness of the model. In this work, we propose an approach to not only predict but also diagnose the outfit compatibility. We introduce an end-to-end framework for this goal, which features for: (1) The overall compatibility is learned from all type-specified pairwise similarities between items, and the backpropagation gradients are used to diagnose the incompatible factors. (2) We leverage the hierarchy of CNN and compare the features at different layers to take into account the compatibilities of different aspects from the low level (such as color, texture) to the high level (such as style). To support the proposed method, we build a new type-specified outfit dataset named Polyvore-T based on Polyvore dataset. We compare our method with the prior state-of-the-art in two tasks: outfit compatibility prediction and fill-in-the-blank. Experiments show that our approach has advantages in both prediction performance and diagnosis ability.

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection. These shortcomings degrade user experience and erode people's trust in all AI systems. In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability. To unify currently available but fragmented approaches toward trustworthy AI, we organize them in a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to system development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items for practitioners and societal stakeholders (e.g., researchers, engineers, and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges for the future development of trustworthy AI systems, where we identify the need for a paradigm shift toward comprehensively trustworthy AI systems.

Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and generating new text of desired properties. Prior work typically learns/finetunes a language model (LM) to perform individual or specific subsets of operations. Recent research has studied combining operations in a plug-and-play manner, often with costly search or optimization in the complex sequence space. This paper proposes a new efficient approach for composable text operations in the compact latent space of text. The low-dimensionality and differentiability of the text latent vector allow us to develop an efficient sampler based on ordinary differential equations (ODEs) given arbitrary plug-in operators (e.g., attribute classifiers). By connecting pretrained LMs (e.g., GPT2) to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. The flexible approach permits diverse control operators (sentiment, tense, formality, keywords, etc.) acquired using any relevant data from different domains. Experiments show that composing those operators within our approach manages to generate or edit high-quality text, substantially improving over previous methods in terms of generation quality and efficiency.

Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the robustness of the system and reduce human labeling costs. In this study, we introduce an unsupervised Adversarial Discriminative Domain Adaptation (ADDA) method to effectively learn an asymmetric mapping that adapts the target domain encoder to the source domain, where the target domain and source domain are speech data from different languages. ADDA, together with a popular Domain Adversarial Training (DAT) approach, are evaluated on a cross-lingual speaker verification task: the training data is in English from NIST SRE04-08, Mixer 6 and Switchboard, and the test data is in Chinese from AISHELL-I. We show that with the ADDA adaptation, Equal Error Rate (EER) of the x-vector system decreases from 9.331\% to 7.645\%, relatively 18.07\% reduction of EER, and 6.32\% reduction from DAT as well. Further data analysis of ADDA adapted speaker embedding shows that the learned speaker embeddings can perform well on speaker classification for the target domain data, and are less dependent with respect to the shift in language.

Although stochastic gradient descent (SGD) method and its variants (e.g., stochastic momentum methods, AdaGrad) are the choice of algorithms for solving non-convex problems (especially deep learning), there still remain big gaps between the theory and the practice with many questions unresolved. For example, there is still a lack of theories of convergence for SGD and its variants that use stagewise step size and return an averaged solution in practice. In addition, theoretical insights of why adaptive step size of AdaGrad could improve non-adaptive step size of {\sgd} is still missing for non-convex optimization. This paper aims to address these questions and fill the gap between theory and practice. We propose a universal stagewise optimization framework for a broad family of {\bf non-smooth non-convex} (namely weakly convex) problems with the following key features: (i) at each stage any suitable stochastic convex optimization algorithms (e.g., SGD or AdaGrad) that return an averaged solution can be employed for minimizing a regularized convex problem; (ii) the step size is decreased in a stagewise manner; (iii) an averaged solution is returned as the final solution that is selected from all stagewise averaged solutions with sampling probabilities {\it increasing} as the stage number. Our theoretical results of stagewise AdaGrad exhibit its adaptive convergence, therefore shed insights on its faster convergence for problems with sparse stochastic gradients than stagewise SGD. To the best of our knowledge, these new results are the first of their kind for addressing the unresolved issues of existing theories mentioned earlier. Besides theoretical contributions, our empirical studies show that our stagewise SGD and ADAGRAD improve the generalization performance of existing variants/implementations of SGD and ADAGRAD.

Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised feature learning, where the design of positive and negative (pos/neg) pairs is one of its keys. In this paper, we attempt to devise a feature-level data manipulation, differing from data augmentation, to enhance the generic contrastive self-supervised learning. To this end, we first design a visualization scheme for pos/neg score (Pos/neg score indicates cosine similarity of pos/neg pair.) distribution, which enables us to analyze, interpret and understand the learning process. To our knowledge, this is the first attempt of its kind. More importantly, leveraging this tool, we gain some significant observations, which inspire our novel Feature Transformation proposals including the extrapolation of positives. This operation creates harder positives to boost the learning because hard positives enable the model to be more view-invariant. Besides, we propose the interpolation among negatives, which provides diversified negatives and makes the model more discriminative. It is the first attempt to deal with both challenges simultaneously. Experiment results show that our proposed Feature Transformation can improve at least 6.0% accuracy on ImageNet-100 over MoCo baseline, and about 2.0% accuracy on ImageNet-1K over the MoCoV2 baseline. Transferring to the downstream tasks successfully demonstrate our model is less task-bias. Visualization tools and codes this https URL .

Recent progress on 2D object detection has featured Cascade RCNN, which capitalizes on a sequence of cascade detectors to progressively improve proposal quality, towards high-quality object detection. However, there has not been evidence in support of building such cascade structures for 3D object detection, a challenging detection scenario with highly sparse LiDAR point clouds. In this work, we present a simple yet effective cascade architecture, named 3D Cascade RCNN, that allocates multiple detectors based on the voxelized point clouds in a cascade paradigm, pursuing higher quality 3D object detector progressively. Furthermore, we quantitatively define the sparsity level of the points within 3D bounding box of each object as the point completeness score, which is exploited as the task weight for each proposal to guide the learning of each stage detector. The spirit behind is to assign higher weights for high-quality proposals with relatively complete point distribution, while down-weight the proposals with extremely sparse points that often incur noise during training. This design of completeness-aware re-weighting elegantly upgrades the cascade paradigm to be better applicable for the sparse input data, without increasing any FLOP budgets. Through extensive experiments on both the KITTI dataset and Waymo Open Dataset, we validate the superiority of our proposed 3D Cascade RCNN, when comparing to state-of-the-art 3D object detection techniques. The source code is publicly available at \url{this https URL}.

Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art performance on many graph representation learning tasks. Currently, at every layer, attention is computed between connected pairs of nodes and depends solely on the representation of the two nodes. However, such attention mechanism does not account for nodes that are not directly connected but provide important network context. Here we propose Multi-hop Attention Graph Neural Network (MAGNA), a principled way to incorporate multi-hop context information into every layer of attention computation. MAGNA diffuses the attention scores across the network, which increases the receptive field for every layer of the GNN. Unlike previous approaches, MAGNA uses a diffusion prior on attention values, to efficiently account for all paths between the pair of disconnected nodes. We demonstrate in theory and experiments that MAGNA captures large-scale structural information in every layer, and has a low-pass effect that eliminates noisy high-frequency information from graph data. Experimental results on node classification as well as the knowledge graph completion benchmarks show that MAGNA achieves state-of-the-art results: MAGNA achieves up to 5.7 percent relative error reduction over the previous state-of-the-art on Cora, Citeseer, and Pubmed. MAGNA also obtains the best performance on a large-scale Open Graph Benchmark dataset. On knowledge graph completion MAGNA advances state-of-the-art on WN18RR and FB15k-237 across four different performance metrics.

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks. Nevertheless, most of existing designs directly employ self-attention over a 2D feature map to obtain the attention matrix based on pairs of isolated queries and keys at each spatial location, but leave the rich contexts among neighbor keys under-exploited. In this work, we design a novel Transformer-style module, i.e., Contextual Transformer (CoT) block, for visual recognition. Such design fully capitalizes on the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthens the capacity of visual representation. Technically, CoT block first contextually encodes input keys via a $3\times3$ convolution, leading to a static contextual representation of inputs. We further concatenate the encoded keys with input queries to learn the dynamic multi-head attention matrix through two consecutive $1\times1$ convolutions. The learnt attention matrix is multiplied by input values to achieve the dynamic contextual representation of inputs. The fusion of the static and dynamic contextual representations are finally taken as outputs. Our CoT block is appealing in the view that it can readily replace each $3\times3$ convolution in ResNet architectures, yielding a Transformer-style backbone named as Contextual Transformer Networks (CoTNet). Through extensive experiments over a wide range of applications (e.g., image recognition, object detection and instance segmentation), we validate the superiority of CoTNet as a stronger backbone. Source code is available at \url{this https URL}.

The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition. However, recent studies have highlighted the lack of robustness in well-trained deep neural networks to adversarial examples. Visually imperceptible perturbations to natural images can easily be crafted and mislead the image classifiers towards misclassification. To demystify the trade-offs between robustness and accuracy, in this paper we thoroughly benchmark 18 ImageNet models using multiple robustness metrics, including the distortion, success rate and transferability of adversarial examples between 306 pairs of models. Our extensive experimental results reveal several new insights: (1) linear scaling law - the empirical $\ell_2$ and $\ell_\infty$ distortion metrics scale linearly with the logarithm of classification error; (2) model architecture is a more critical factor to robustness than model size, and the disclosed accuracy-robustness Pareto frontier can be used as an evaluation criterion for ImageNet model designers; (3) for a similar network architecture, increasing network depth slightly improves robustness in $\ell_\infty$ distortion; (4) there exist models (in VGG family) that exhibit high adversarial transferability, while most adversarial examples crafted from one model can only be transferred within the same family. Experiment code is publicly available at \url{this https URL}.

Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial intelligence field involve multiple modalities. Therefore, it is of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, we provide a technical review of available models and learning methods for multimodal intelligence. The main focus of this review is the combination of vision and natural language modalities, which has become an important topic in both the computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications. Regarding multimodal representation learning, we review the key concepts of embedding, which unify multimodal signals into a single vector space and thereby enable cross-modality signal processing. We also review the properties of many types of embeddings that are constructed and learned for general downstream tasks. Regarding multimodal fusion, this review focuses on special architectures for the integration of representations of unimodal signals for a particular task. Regarding applications, selected areas of a broad interest in the current literature are covered, including image-to-text caption generation, text-to-image generation, and visual question answering. We believe that this review will facilitate future studies in the emerging field of multimodal intelligence for related communities.

Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are prone to over-fitting due to the increasing number of parameters and the lack of direct supervision on attention weights. GATs also suffer from over-smoothing at the decision boundary of nodes. Here we propose a framework to address their weaknesses via margin-based constraints on attention during training. We first theoretically demonstrate the over-smoothing behavior of GATs and then develop an approach using constraint on the attention weights according to the class boundary and feature aggregation pattern. Furthermore, to alleviate the over-fitting problem, we propose additional constraints on the graph structure. Extensive experiments and ablation studies on common benchmark datasets demonstrate the effectiveness of our method, which leads to significant improvements over the previous state-of-the-art graph attention methods on all datasets.

This paper proposes an expressive singing voice synthesis system by introducing explicit vibrato modeling and latent energy representation. Vibrato is essential to the naturalness of synthesized sound, due to the inherent characteristics of human singing. Hence, a deep learning-based vibrato model is introduced in this paper to control the vibrato's likeliness, rate, depth and phase in singing, where the vibrato likeliness represents the existence probability of vibrato and it would help improve the singing voice's naturalness. Actually, there is no annotated label about vibrato likeliness in existing singing corpus. We adopt a novel vibrato likeliness labeling method to label the vibrato likeliness automatically. Meanwhile, the power spectrogram of audio contains rich information that can improve the expressiveness of singing. An autoencoder-based latent energy bottleneck feature is proposed for expressive singing voice synthesis. Experimental results on the open dataset NUS48E show that both the vibrato modeling and the latent energy representation could significantly improve the expressiveness of singing voice. The audio samples are shown in the demo website.