Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. However, the limited scale and diversity of current image-text interleaved data restrict the development of multimodal large language models. In this paper, we introduce OmniCorpus, a 10 billion-level image-text interleaved dataset. Using an efficient data engine, we filter and extract large-scale high-quality documents, which contain 8.6 billion images and 1,696 billion text tokens. Compared to counterparts (e.g., MMC4, OBELICS), our dataset 1) has 15 times larger scales while maintaining good data quality; 2) features more diverse sources, including both English and non-English websites as well as video-centric websites; 3) is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs. Through comprehensive analysis and experiments, we validate the quality, usability, and effectiveness of the proposed dataset. We hope this could provide a solid data foundation for future multimodal model research.

Although the automatic identification of the optimal fingering for the performance of melodies on fretted string instruments has already been addressed (at least partially) in the literature, the specific case regarding lead electric guitar requires a dedicated approach. We propose a system that can generate, from simple MIDI melodies, tablatures enriched by fingerings, articulations, and expressive techniques. The basic fingering is derived by solving a constrained and multi-attribute optimization problem, which derives the best position of the fretting hand, not just the finger used at each moment.Then, by analyzing statistical data from the mySongBook corpus, the most common clich{\'e}s and biomechanical feasibility, articulations, and expressive techniques are introduced. Finally, the obtained output is converted into MusicXML format, which allows for easy visualization and use. The quality of the tablatures derived and the high configurability of the proposed approach can have several impacts, in particular in the fields of instrumental teaching, assisted composition and arranging, and computational expressive music performance models.

Autoregressive generative transformers are key in music generation, producing coherent compositions but facing challenges in human-machine collaboration. We propose RefinPaint, an iterative technique that improves the sampling process. It does this by identifying the weaker music elements using a feedback model, which then informs the choices for resampling by an inpainting model. This dual-focus methodology not only facilitates the machine's ability to improve its automatic inpainting generation through repeated cycles but also offers a valuable tool for humans seeking to refine their compositions with automatic proofreading. Experimental results suggest RefinPaint's effectiveness in inpainting and proofreading tasks, demonstrating its value for refining music created by both machines and humans. This approach not only facilitates creativity but also aids amateur composers in improving their work.

Text-to-image diffusion models benefit artists with high-quality image generation. Yet their stochastic nature hinders artists from creating consistent images of the same subject. Existing methods try to tackle this challenge and generate consistent content in various ways. However, they either depend on external restricted data or require expensive tuning of the diffusion model. For this issue, we propose a novel one-shot tuning paradigm, termed as OneActor. It efficiently performs consistent subject generation solely driven by prompts via a learned semantic guidance to bypass the laborious backbone tuning. We lead the way to formalize the objective of consistent subject generation from a clustering perspective, and thus design a cluster-conditioned model. To mitigate the overfitting challenge shared by one-shot tuning pipelines, we augment the tuning with auxiliary samples and devise two inference strategies: semantic interpolation and cluster guidance. These techniques are later verified to significantly enhance the generation quality. Comprehensive experiments show that our method outperforms a variety of baselines with satisfactory subject consistency, superior prompt conformity as well as high image quality. Our method is capable of multi-subject generation and compatible with popular diffusion extensions. Besides, we achieve a 4 times faster tuning speed than tuning-based baselines and, if desired, avoid increasing inference time. Furthermore, to our best knowledge, we are the first to prove that the semantic space of the diffusion model has the same interpolation property as the latent space does. This property can serve as another promising tool for fine generation control.

Science journalism reports current scientific discoveries to non-specialists, aiming to enable public comprehension of the state of the art. However, this task can be challenging as the audience often lacks specific knowledge about the presented research. To address this challenge, we propose a framework that integrates three LLMs mimicking the real-world writing-reading-feedback-revision workflow, with one LLM acting as the journalist, a smaller LLM as the general public reader, and the third LLM as an editor. The journalist's writing is iteratively refined by feedback from the reader and suggestions from the editor. Our experiments demonstrate that by leveraging the collaboration of two 7B and one 1.8B open-source LLMs, we can generate articles that are more accessible than those generated by existing methods, including advanced models such as GPT-4.

Pre-trained models learn general representations from large datsets which can be fine-turned for specific tasks to significantly reduce training time. Pre-trained models like generative pretrained transformers (GPT), bidirectional encoder representations from transformers (BERT), vision transfomers (ViT) have become a cornerstone of current research in machine learning. This study proposes a multi-modal movie recommendation system by extract features of the well designed posters for each movie and the narrative text description of the movie. This system uses the BERT model to extract the information of text modality, the ViT model applied to extract the information of poster/image modality, and the Transformer architecture for feature fusion of all modalities to predict users' preference. The integration of pre-trained foundational models with some smaller data sets in downstream applications capture multi-modal content features in a more comprehensive manner, thereby providing more accurate recommendations. The efficiency of the proof-of-concept model is verified by the standard benchmark problem the MovieLens 100K and 1M datasets. The prediction accuracy of user ratings is enhanced in comparison to the baseline algorithm, thereby demonstrating the potential of this cross-modal algorithm to be applied for movie or video recommendation.

In recent years, journalists have expressed concerns about the increasing trend of news article avoidance, especially within specific domains. This issue has been exacerbated by the rise of recommender systems. Our research indicates that recommender systems should consider avoidance as a fundamental factor. We argue that news articles can be characterized by three principal elements: exposure, relevance, and avoidance, all of which are closely interconnected. To address these challenges, we introduce AWRS, an Avoidance-Aware Recommender System. This framework incorporates avoidance awareness when recommending news, based on the premise that news article avoidance conveys significant information about user preferences. Evaluation results on three news datasets in different languages (English, Norwegian, and Japanese) demonstrate that our method outperforms existing approaches.

This paper presents a novel and comprehensive solution to enhance both the robustness and efficiency of question answering (QA) systems through supervised contrastive learning (SCL). Training a high-performance QA system has become straightforward with pre-trained language models, requiring only a small amount of data and simple fine-tuning. However, despite recent advances, existing QA systems still exhibit significant deficiencies in functionality and training efficiency. We address the functionality issue by defining four key tasks: user input intent classification, out-of-domain input detection, new intent discovery, and continual learning. We then leverage a unified SCL-based representation learning method to efficiently build an intra-class compact and inter-class scattered feature space, facilitating both known intent classification and unknown intent detection and discovery. Consequently, with minimal additional tuning on downstream tasks, our approach significantly improves model efficiency and achieves new state-of-the-art performance across all tasks.

Words often carry different meanings for people from diverse backgrounds. Today's era of social polarization demands that we choose words carefully to prevent miscommunication, especially in political communication and journalism. To address this issue, we introduce the Bridging Dictionary, an interactive tool designed to illuminate how words are perceived by people with different political views. The Bridging Dictionary includes a static, printable document featuring 796 terms with summaries generated by a large language model. These summaries highlight how the terms are used distinctively by Republicans and Democrats. Additionally, the Bridging Dictionary offers an interactive interface that lets users explore selected words, visualizing their frequency, sentiment, summaries, and examples across political divides. We present a use case for journalists and emphasize the importance of human agency and trust in further enhancing this tool. The deployed version of Bridging Dictionary is available at https://dictionary.ccc-mit.org/.

This work explores how to fine-tune large language models using prompt engineering techniques with contextual information for generating an accurate text description of the full story, ready to be forwarded to off-the-shelve speech synthesis tools. We propose to use existing computer vision and optical character recognition techniques to build a grounded context from the comic strip image content, such as panels, characters, text, reading order and the association of bubbles and characters. Then we infer character identification and generate comic book script with context-aware panel description including character's appearance, posture, mood, dialogues etc. We believe that such enriched content description can be easily used to produce audiobook and eBook with various voices for characters, captions and playing sound effects. Keywords: comics understanding large language model prompt engineering character identification comic book script accessible comics.