In Multimodal Language Models (MLMs), the cost of manually annotating high-quality image-text pair data for fine-tuning and alignment is extremely high. While existing multimodal data augmentation frameworks propose ways to augment image-text pairs, they either suffer from semantic inconsistency between texts and images, or generate unrealistic images, causing knowledge gap with real world examples. To address these issues, we propose Attribute-based Multimodal Data Augmentation (ARMADA), a novel multimodal data augmentation method via knowledge-guided manipulation of visual attributes of the mentioned entities. Specifically, we extract entities and their visual attributes from the original text data, then search for alternative values for the visual attributes under the guidance of knowledge bases (KBs) and large language models (LLMs). We then utilize an image-editing model to edit the images with the extracted attributes. ARMADA is a novel multimodal data generation framework that: (i) extracts knowledge-grounded attributes from symbolic KBs for semantically consistent yet distinctive image-text pair generation, (ii) generates visually similar images of disparate categories using neighboring entities in the KB hierarchy, and (iii) uses the commonsense knowledge of LLMs to modulate auxiliary visual attributes such as backgrounds for more robust representation of original entities. Our empirical results over four downstream tasks demonstrate the efficacy of our framework to produce high-quality data and enhance the model performance. This also highlights the need to leverage external knowledge proxies for enhanced interpretability and real-world grounding.

Sign Language Translation (SLT) is a core task in the field of AI-assisted disability. Unlike traditional SLT based on visible light videos, which is easily affected by factors such as lighting, rapid hand movements, and privacy breaches, this paper proposes the use of high-definition Event streams for SLT, effectively mitigating the aforementioned issues. This is primarily because Event streams have a high dynamic range and dense temporal signals, which can withstand low illumination and motion blur well. Additionally, due to their sparsity in space, they effectively protect the privacy of the target person. More specifically, we propose a new high-resolution Event stream sign language dataset, termed Event-CSL, which effectively fills the data gap in this area of research. It contains 14,827 videos, 14,821 glosses, and 2,544 Chinese words in the text vocabulary. These samples are collected in a variety of indoor and outdoor scenes, encompassing multiple angles, light intensities, and camera movements. We have benchmarked existing mainstream SLT works to enable fair comparison for future efforts. Based on this dataset and several other large-scale datasets, we propose a novel baseline method that fully leverages the Mamba model's ability to integrate temporal information of CNN features, resulting in improved sign language translation outcomes. Both the benchmark dataset and source code will be released on https://github.com/Event-AHU/OpenESL

A song about immigrants whose music, vocals and artwork were entirely generated using artificial intelligence has made the Top 50 most listened to songs in Germany, in what may be a first for a leading music market. Verknallt in einen Talahon is a parody song that weaves modern lyrics – many of them based around racial stereotypes about immigrants – with 60s schlager pop. The song is No 48 in Germany, the world's fourth largest music market. Less than a month after its release, the song has 3.5m streams on Spotify and is No 3 on the streaming platform's global viral chart. Its creator, Josua Waghubinger, who goes by the artist name Butterbro, said he made the song's chorus by feeding his own lyrics into Udio, a generative artificial intelligence tool that can generate vocals and instrumentation from simple text prompts.

In recommender systems, popularity and conformity biases undermine recommender effectiveness by disproportionately favouring popular items, leading to their over-representation in recommendation lists and causing an unbalanced distribution of user-item historical data. We construct a causal graph to address both biases and describe the abstract data generation mechanism. Then, we use it as a guide to develop a novel Debiased Contrastive Learning framework for Mitigating Dual Biases, called DCLMDB. In DCLMDB, both popularity bias and conformity bias are handled in the model training process by contrastive learning to ensure that user choices and recommended items are not unduly influenced by conformity and popularity. Extensive experiments on two real-world datasets, Movielens-10M and Netflix, show that DCLMDB can effectively reduce the dual biases, as well as significantly enhance the accuracy and diversity of recommendations.

In recommender systems, latent variables can cause user-item interaction data to deviate from true user preferences. This biased data is then used to train recommendation models, further amplifying the bias and ultimately compromising both recommendation accuracy and user satisfaction. Instrumental Variable (IV) methods are effective tools for addressing the confounding bias introduced by latent variables; however, identifying a valid IV is often challenging. To overcome this issue, we propose a novel data-driven conditional IV (CIV) debiasing method for recommender systems, called CIV4Rec. CIV4Rec automatically generates valid CIVs and their corresponding conditioning sets directly from interaction data, significantly reducing the complexity of IV selection while effectively mitigating the confounding bias caused by latent variables in recommender systems. Specifically, CIV4Rec leverages a variational autoencoder (VAE) to generate the representations of the CIV and its conditional set from interaction data, followed by the application of least squares to derive causal representations for click prediction. Extensive experiments on two real-world datasets, Movielens-10M and Douban-Movie, demonstrate that our CIV4Rec successfully identifies valid CIVs, effectively reduces bias, and consequently improves recommendation accuracy.

Quality assessment, which evaluates the visual quality level of multimedia experiences, has garnered significant attention from researchers and has evolved substantially through dedicated efforts. Before the advent of large models, quality assessment typically relied on small expert models tailored for specific tasks. While these smaller models are effective at handling their designated tasks and predicting quality levels, they often lack explainability and robustness. With the advancement of large models, which align more closely with human cognitive and perceptual processes, many researchers are now leveraging the prior knowledge embedded in these large models for quality assessment tasks. This emergence of quality assessment within the context of large models motivates us to provide a comprehensive review focusing on two key aspects: 1) the assessment of large models, and 2) the role of large models in assessment tasks. We begin by reflecting on the historical development of quality assessment. Subsequently, we move to detailed discussions of related works concerning quality assessment in the era of large models. Finally, we offer insights into the future progression and potential pathways for quality assessment in this new era. We hope this survey will enable a rapid understanding of the development of quality assessment in the era of large models and inspire further advancements in the field.

Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a naive fusion of depth information can disrupt feature and compromise accuracy due to the modality gap between the depth and the vision. In this work, we introduce a Depth-guided Texture Diffusion approach that effectively tackles the outlined challenge. Our method extracts low-level features from edges and textures to create a texture image. This image is then selectively diffused across the depth map, enhancing structural information vital for precisely extracting object outlines. By integrating this enriched depth map with the original RGB image into a joint feature embedding, our method effectively bridges the disparity between the depth map and the image, enabling more accurate semantic segmentation. We conduct comprehensive experiments across diverse, commonly-used datasets spanning a wide range of semantic segmentation tasks, including Camouflaged Object Detection (COD), Salient Object Detection (SOD), and indoor semantic segmentation. With source-free estimated depth or depth captured by depth cameras, our method consistently outperforms existing baselines and achieves new state-of-theart results, demonstrating the effectiveness of our Depth-guided Texture Diffusion for image semantic segmentation.

An increasing number of media streaming services have expanded their offerings to include entities of multiple content types. For instance, audio streaming services that started by offering music only, now also offer podcasts, merchandise items, and videos. Ranking items across different content types into a single slate poses a significant challenge for traditional learning-to-rank (LTR) algorithms due to differing user engagement patterns for different content types. We explore a simple method for cross-content-type ranking, called multinomial blending (MB), which can be used in conjunction with most existing LTR algorithms. We compare MB to existing baselines not only in terms of ranking quality but also from other industry-relevant perspectives such as interpretability, ease-of-use, and stability in dynamic environments with changing user behavior and ranking model retraining. Finally, we report the results of an A/B test from an Amazon Music ranking use-case.

OpenAI said on Friday that it thwarted an Iranian influence campaign that used ChatGPT to generate fake news stories and social posts aimed at Americans. The company said it identified and banned accounts generating content for five websites (in English and Spanish) pretending to be news outlets, spreading "polarizing messages" on issues like the US presidential campaign, LGBTQ rights and the war in Gaza. The operation was identified as "Storm-2035," part of a series of influence campaigns Microsoft identified last week as "connected with the Iranian government." In addition to the news posts, it included "a dozen accounts on X and one on Instagram" connected to the operation. OpenAI said the op didn't appear to have gained any meaningful traction.

This week, X launched an AI-image generator, allowing paying subscribers of Elon Musk's social platform to make their own art. So--naturally--some users appear to have immediately made images of Donald Trump flying a plane toward the World Trade Center; Mickey Mouse wielding an assault rifle, and another of him enjoying a cigarette and some beer on the beach; and so on. Some of the images that people have created using the tool are deeply unsettling; others are just strange, or even kind of funny. They depict wildly different scenarios and characters. But somehow they all kind of look alike, bearing unmistakable hallmarks of AI art that have cropped up in recent years thanks to products such as Midjourney and DALL-E.