Hasil untuk "Manners and customs (General)"

Maomao Li, Zhen Li, Kaipeng Zhang et al.

Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advancement of joint audio-video generation, this paper proposes a more compelling new task: sync audio-video customization, which aims to synchronously customize both video identity and audio timbre. Specifically, given a reference image $I^{r}$ and a reference audio $A^{r}$, this novel task requires generating videos that maintain the identity of the reference image while imitating the timbre of the reference audio, with spoken content freely specifiable through user-provided textual prompts. To this end, we propose OmniCustom, a powerful DiT-based audio-video customization framework that can synthesize a video following reference image identity, audio timbre, and text prompts all at once in a zero-shot manner. Our framework is built on three key contributions. First, identity and audio timbre control are achieved through separate reference identity and audio LoRA modules that operate through self-attention layers within the base audio-video generation model. Second, we introduce a contrastive learning objective alongside the standard flow matching objective. It uses predicted flows conditioned on reference inputs as positive examples and those without reference conditions as negative examples, thereby enhancing the model ability to preserve identity and timbre. Third, we train OmniCustom on our constructed large-scale, high-quality audio-visual human dataset. Extensive experiments demonstrate that OmniCustom outperforms existing methods in generating audio-video content with consistent identity and timbre fidelity. Project page: https://omnicustom-project.github.io/page/.

Geovane Souza Melo Junior

Este artigo investiga de que modo a obra cinematográfica de Sylvio Back instaura uma poética da mon­tagem crítica, na qual literatura e história se entrelaçam como instâncias de reconfiguração simbólica do tempo. Longe de estabelecer filiações diretas, o estudo mobiliza conceitos como o tempo messiânico de Walter Benjamin e a imagem-tempo de Gilles Deleuze, a fim de iluminar os procedimentos estéticos que desestabilizam tanto a linearidade narrativa quanto as convenções da historiografia dominante. A recorrência de figuras históricas marginalizadas, aliada à tessitura de referências literárias, evidencia a construção de uma escrita cinematográfica híbrida, na qual suas películas operam como arquivos do dissenso. Em suma, argumenta-se que, em Back, o cinema não se limita a representar o passado, mas o reinscreve como interrogação, instaurando um regime de temporalidade crítica que desafia as fronteiras entre documento, ficção e memória.

Yaowei Li, Xiaoyu Li, Zhaoyang Zhang et al.

Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-aware and position-free image customization through in-context learning. IC-Custom concatenates reference images with target images to a polyptych, leveraging DiT's multi-modal attention mechanism for fine-grained token-level interactions. We propose the In-context Multi-Modal Attention (ICMA) mechanism, which employs learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to effectively handle diverse tasks and distinguish between inputs in polyptych configurations. To address the data gap, we curated a 12K identity-consistent dataset with 8K real-world and 4K high-quality synthetic samples, avoiding the overly glossy, oversaturated look typical of synthetic data. IC-Custom supports various industrial applications, including try-on, image insertion, and creative IP customization. Extensive evaluations on our proposed ProductBench and the publicly available DreamBench demonstrate that IC-Custom significantly outperforms community workflows, closed-source models, and state-of-the-art open-source approaches. IC-Custom achieves about 73\% higher human preference across identity consistency, harmony, and text alignment metrics, while training only 0.4\% of the original model parameters. Project page: https://liyaowei-stu.github.io/project/IC_Custom

Guandong Li, Zhaobin Chu

We propose EditID, a training-free approach based on the DiT architecture, which achieves highly editable customized IDs for text to image generation. Existing text-to-image models for customized IDs typically focus more on ID consistency while neglecting editability. It is challenging to alter facial orientation, character attributes, and other features through prompts. EditID addresses this by deconstructing the text-to-image model for customized IDs into an image generation branch and a character feature branch. The character feature branch is further decoupled into three modules: feature extraction, feature fusion, and feature integration. By introducing a combination of mapping features and shift features, along with controlling the intensity of ID feature integration, EditID achieves semantic compression of local features across network depths, forming an editable feature space. This enables the successful generation of high-quality images with editable IDs while maintaining ID consistency, achieving excellent results in the IBench evaluation, which is an editability evaluation framework for the field of customized ID text-to-image generation that quantitatively demonstrates the superior performance of EditID. EditID is the first text-to-image solution to propose customizable ID editability on the DiT architecture, meeting the demands of long prompts and high quality image generation.

Jann Zosso

Guided by the Einstein equivalence principle that identifies the phenomenon of gravitation as a manifestation of the dynamics of spacetime in contrast to a localizable force, we review and explore its consequences on formulating a theory of gravity. The resulting space of metric theories of gravity may address open conceptual and observational puzzles through a wealth of effects beyond general relativity, whose traces can be searched for within today's and tomorrow's gravitational testing grounds. Above all, we offer a generic metric theory generalization of Isaacson's approach to the leading-order field equations of physical perturbations with a well-defined notion of energy-momentum carried by the gravitational waves. Within this framework, we identify the backreaction of the Isaacson energy-momentum flux onto the background spacetime with the displacement memory effect that induces a permanent distortion of space after the passage of a gravitational wave. This effect is a well-known prediction of GR whose dominant contribution captures its inherent non-linear nature, manifest in the ability of gravity to gravitate. However, the novel interpretation of memory as naturally arising within the Isaacson approach to gravitational waves comes with two main advantages. Firstly, it allows for a unified understanding of both the null and the ordinary memory effect, which are respectively sourced by unbound energy fluxes that do and do not reach asymptotic null infinity. Secondly, and most importantly, this approach allows for a consistent derivation of the memory formula for a large class of metric theories with considerable lessons to be learned for upcoming future measurements of the memory effect.

Zhentao Xu, Mark Jerome Cruz, Matthew Guevara et al.

In customer service technical support, swiftly and accurately retrieving relevant past issues is critical for efficiently resolving customer inquiries. The conventional retrieval methods in retrieval-augmented generation (RAG) for large language models (LLMs) treat a large corpus of past issue tracking tickets as plain text, ignoring the crucial intra-issue structure and inter-issue relations, which limits performance. We introduce a novel customer service question-answering method that amalgamates RAG with a knowledge graph (KG). Our method constructs a KG from historical issues for use in retrieval, retaining the intra-issue structure and inter-issue relations. During the question-answering phase, our method parses consumer queries and retrieves related sub-graphs from the KG to generate answers. This integration of a KG not only improves retrieval accuracy by preserving customer service structure information but also enhances answering quality by mitigating the effects of text segmentation. Empirical assessments on our benchmark datasets, utilizing key retrieval (MRR, Recall@K, NDCG@K) and text generation (BLEU, ROUGE, METEOR) metrics, reveal that our method outperforms the baseline by 77.6% in MRR and by 0.32 in BLEU. Our method has been deployed within LinkedIn's customer service team for approximately six months and has reduced the median per-issue resolution time by 28.6%.

Ganggui Ding, Canyu Zhao, Wen Wang et al.

Benefiting from large-scale pre-trained text-to-image (T2I) generative models, impressive progress has been achieved in customized image generation, which aims to generate user-specified concepts. Existing approaches have extensively focused on single-concept customization and still encounter challenges when it comes to complex scenarios that involve combining multiple concepts. These approaches often require retraining/fine-tuning using a few images, leading to time-consuming training processes and impeding their swift implementation. Furthermore, the reliance on multiple images to represent a singular concept increases the difficulty of customization. To this end, we propose FreeCustom, a novel tuning-free method to generate customized images of multi-concept composition based on reference concepts, using only one image per concept as input. Specifically, we introduce a new multi-reference self-attention (MRSA) mechanism and a weighted mask strategy that enables the generated image to access and focus more on the reference concepts. In addition, MRSA leverages our key finding that input concepts are better preserved when providing images with context interactions. Experiments show that our method's produced images are consistent with the given concepts and better aligned with the input text. Our method outperforms or performs on par with other training-based methods in terms of multi-concept composition and single-concept customization, but is simpler. Codes can be found at https://github.com/aim-uofa/FreeCustom.

Sarah Uszynski, Sabrina Sedlmayer

A pesquisa aqui abordada parte da obra Estação Carandiru, de Drauzio Varella e busca analisar as táticas elaboradas pelos detentos da Casa de Detenção de São Paulo, considerada, até então, a maior penitenciária do país, o Carandiru, com o objetivo de localizar estratégias de sobrevivência diante da falta e da escassez das suas vidas em cárcere. Perpassando por questões que envolvem o conceito de gambiarra, discorreremos sobre algumas das táticas relacionadas ao campo da alimentação, como o fogareiro, o recorte e a Maria-Louca. A hipótese que se desenha é a de que há um intenso vínculo entre a gambiarra e a sobrevivência no contexto penitenciário, e a Maria-Louca, funciona como um modus operandi, na tentativa, muitas vezes eficaz, de subverter as adversidades vividas pelo sujeito carcerário.

Zhendong Wang, Jianmin Bao, Wengang Zhou et al.

Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a detector for telling apart real images from diffusion-generated images. We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data. To address this issue, we propose a novel image representation called DIffusion Reconstruction Error (DIRE), which measures the error between an input image and its reconstruction counterpart by a pre-trained diffusion model. We observe that diffusion-generated images can be approximately reconstructed by a diffusion model while real images cannot. It provides a hint that DIRE can serve as a bridge to distinguish generated and real images. DIRE provides an effective way to detect images generated by most diffusion models, and it is general for detecting generated images from unseen diffusion models and robust to various perturbations. Furthermore, we establish a comprehensive diffusion-generated benchmark including images generated by eight diffusion models to evaluate the performance of diffusion-generated image detectors. Extensive experiments on our collected benchmark demonstrate that DIRE exhibits superiority over previous generated-image detectors. The code and dataset are available at https://github.com/ZhendongWang6/DIRE.

Yu-Chien Tang, Wei-Yao Wang, An-Zi Yen et al.

The dialogue systems in customer services have been developed with neural models to provide users with precise answers and round-the-clock support in task-oriented conversations by detecting customer intents based on their utterances. Existing intent detection approaches have highly relied on adaptively pre-training language models with large-scale datasets, yet the predominant cost of data collection may hinder their superiority. In addition, they neglect the information within the conversational responses of the agents, which have a lower collection cost, but are significant to customer intent as agents must tailor their replies based on the customers' intent. In this paper, we propose RSVP, a self-supervised framework dedicated to task-oriented dialogues, which utilizes agent responses for pre-training in a two-stage manner. Specifically, we introduce two pre-training tasks to incorporate the relations of utterance-response pairs: 1) Response Retrieval by selecting a correct response from a batch of candidates, and 2) Response Generation by mimicking agents to generate the response to a given utterance. Our benchmark results for two real-world customer service datasets show that RSVP significantly outperforms the state-of-the-art baselines by 4.95% for accuracy, 3.4% for MRR@3, and 2.75% for MRR@5 on average. Extensive case studies are investigated to show the validity of incorporating agent responses into the pre-training stage.

Wenxing Xu, Yuanchun Li, Jiacheng Liu et al.

Unlike cloud-based deep learning models that are often large and uniform, edge-deployed models usually demand customization for domain-specific tasks and resource-limited environments. Such customization processes can be costly and time-consuming due to the diversity of edge scenarios and the training load for each scenario. Although various approaches have been proposed for rapid resource-oriented customization and task-oriented customization respectively, achieving both of them at the same time is challenging. Drawing inspiration from the generative AI and the modular composability of neural networks, we introduce NN-Factory, an one-for-all framework to generate customized lightweight models for diverse edge scenarios. The key idea is to use a generative model to directly produce the customized models, instead of training them. The main components of NN-Factory include a modular supernet with pretrained modules that can be conditionally activated to accomplish different tasks and a generative module assembler that manipulate the modules according to task and sparsity requirements. Given an edge scenario, NN-Factory can efficiently customize a compact model specialized in the edge task while satisfying the edge resource constraints by searching for the optimal strategy to assemble the modules. Based on experiments on image classification and object detection tasks with different edge devices, NN-Factory is able to generate high-quality task- and resource-specific models within few seconds, faster than conventional model customization approaches by orders of magnitude.

Zhenyi Wang, Hongcai Zhang

Customers' load profiles are critical resources to support data analytics applications in modern power systems. However, there are usually insufficient historical load profiles for data analysis, due to the collection cost and data privacy issues. To address such data shortage problems, load profiles synthesis is an effective technique that provides synthetic training data for customers to build high-performance data-driven models. Nonetheless, it is still challenging to synthesize high-quality load profiles for each customer using generation models trained by the respective customer's data owing to the high heterogeneity of customer load. In this paper, we propose a novel customized load profiles synthesis method based on conditional diffusion models for heterogeneous customers. Specifically, we first convert the customized synthesis into a conditional data generation issue. We then extend traditional diffusion models to conditional diffusion models to realize conditional data generation, which can synthesize exclusive load profiles for each customer according to the customer's load characteristics and application demands. In addition, to implement conditional diffusion models, we design a noise estimation model with stacked residual layers, which improves the generation performance by using skip connections. The attention mechanism is also utilized to better extract the complex temporal dependency of load profiles. Finally, numerical case studies based on a public dataset are conducted to validate the effectiveness and superiority of the proposed method.

Yulong Li, Andy Zeng, Shuran Song

Most successes in autonomous robotic assembly have been restricted to single target or category. We propose to investigate general part assembly, the task of creating novel target assemblies with unseen part shapes. As a fundamental step to a general part assembly system, we tackle the task of determining the precise poses of the parts in the target assembly, which we we term ``rearrangement planning''. We present General Part Assembly Transformer (GPAT), a transformer-based model architecture that accurately predicts part poses by inferring how each part shape corresponds to the target shape. Our experiments on both 3D CAD models and real-world scans demonstrate GPAT's generalization abilities to novel and diverse target and part shapes.

Cíntia Roberto Marson

Este artigo tem como objetivo analisar a narrativa juvenil intitulada Minuano, de Tabajara Ruas, sob a perspectiva da metaficção historiográfica, de Linda Hutcheon (1991). Na obra, o escritor sul-rio-grandense realiza uma releitura da Guerra dos Farrapos, conferindo voz e vez aos silenciados pelo discurso da história oficial. Pretendemos, então, evidenciar elementos da metaficção historiográfica construídos ao longo do enredo e de que maneira a obra pode contribuir para a formação do leitor crítico, capaz de refletir sobre si e o mundo que o cerca.

Carlos Wender Sousa Silva

Este artigo busca apontar a ressignificação dada pela literatura brasileira contemporânea às manifestações da violência, nos âmbitos institucional e privado, a partir da obra literária Gog Magog, de Patrícia Melo (2017). Discute-se, então, em que medida a obra literária consegue apreender a indiferença, o ódio e a violência decorrentes das relações humanas fragmentadas na contemporaneidade. Para isso, este texto está dividido em cinco momentos: o Brasil das estatísticas chega ao romance, a literatura como questionamento do imediatismo e da dissolução das relações humanas; quando o diálogo é interrompido; o barulho como representação da incomunicabilidade; e por fim, as delimitações entre a violência estrutural e aquelas refletidas na vida privada.

Luciana Brandão Leal

Neste artigo, apresenta-se uma leitura dos poemas de Virgílio de Lemos com o objetivo de analisar os percursos diaspóricos propostos por esse escritor em diversos momentos de sua obra, para então situá-lo no cenário da moderna poesia moçambicana. Tais reflexões amparam-se no conceito de diáspora proposto por Stuart Hall (2011) e retomado por Prisca Agustoni (2013) que consideram os movimentos diaspóricos de pessoas, ideias e signos, não se limitando ao deslocamento físico.

Rafael Balseiro Zin

Os primeiros registros da literatura de autoria negra no Brasil datam do início da segunda metade do século XIX, sendo os seus precursores Luiz Gama (1830-1882), com a publicação de suas Primeiras trovas burlescas de Getulino, em 1859, na cidade de São Paulo, e Maria Firmina dos Reis (1822-1917), com a publicação do romance Úrsula, também em 1859, na cidade de São Luís do Maranhão. Contudo, até hoje, mesmo tendo se passado cerca de 160 anos da publicação primeira dessas obras inaugurais, tantos os autores quanto seus escritos continuam sendo desconhecidos pela maioria da nossa população. Se o acesso à literatura deve ser entendido como um direito básico de todos os seres humanos, como sugeriu Antonio Candido em seu clássico ensaio O direito à literatura, por que determinadas vertentes da nossa criação literária, como a literatura afro-brasileira, por exemplo, continuam sendo renegadas por uma parcela considerável da nossa Academia, ignoradas pelos grandes conglomerados do mercado editorial brasileiro ou mesmo desprestigiadas em meio à crítica e ao público leitor? Se a literatura é, de fato, um direito fundamental de todos os indivíduos, afinal, de qual literatura estamos tratando? Tomando esses questionamentos como ponto de partida, o presente artigo tem como objetivo refletir sobre a relação existente entre a formação do cânone literário brasileiro, o racismo e o sexismo que assolam o conjunto da nossa sociedade, buscando, num primeiro momento, dialogar com as ideias do sociólogo e crítico literário contidas em seu ensaio, para, logo em seguida, reavaliar o alcance e os sentidos possíveis desse direito fundamental.

Prathamesh Muzumdar, George Kurian

This study tries to examine the influence of salesperson's customer orientation on customer loyalty. Customer orientation is the approach taken by a salesperson to improve customer relationship and increase sales. Many organizations prefer sales orientation as a strategic approach towards increasing sales. Though successful in its objective, sales orientation fails to attract repetitive purchase. It has become a necessity to train frontline employees to better understand the customer needs, keeping in mind the firm's ultimate objective. This study examines the improvements customer orientation can bring to increase repurchases thus leading to customer loyalty. The findings suggest that product assortment, long lines of customers, customers' annual income, and the listening skills of salesperson were the significant antecedents of customer loyalty.

Administrador Veredas

Vineeth Kashyap, Jason Ruchti, Lucja Kot et al.

We introduce Bug-Injector, a system that automatically creates benchmarks for customized evaluation of static analysis tools. We share a benchmark generated using Bug-Injector and illustrate its efficacy by using it to evaluate the recall of two leading open-source static analysis tools: Clang Static Analyzer and Infer. Bug-Injector works by inserting bugs based on bug templates into real-world host programs. It runs tests on the host program to collect dynamic traces, searches the traces for a point where the state satisfies the preconditions for some bug template, then modifies the host program to inject a bug based on that template. Injected bugs are used as test cases in a static analysis tool evaluation benchmark. Every test case is accompanied by a program input that exercises the injected bug. We have identified a broad range of requirements and desiderata for bug benchmarks; our approach generates on-demand test benchmarks that meet these requirements. It also allows us to create customized benchmarks suitable for evaluating tools for a specific use case (e.g., a given codebase and set of bug types). Our experimental evaluation demonstrates the suitability of our generated benchmark for evaluating static bug-detection tools and for comparing the performance of different tools.