Large language models have made significant strides in natural language processing, paving the way for innovative applications including molecular representation and generation. However, most existing single-modality approaches cannot capture the abundant and complex information in molecular data. Here, we introduce GIT-Mol, a multi-modal large language model that integrates the structure Graph, Image, and Text information, including the Simplified Molecular Input Line Entry System (SMILES) and molecular captions. To facilitate the integration of multi-modal molecular data, we propose GIT-Former, a novel architecture capable of mapping all modalities into a unified latent space. Our study develops an innovative any-to-language molecular translation strategy and achieves a 10%-15% improvement in molecular captioning, a 5%-10% accuracy increase in property prediction, and a 20% boost in molecule generation validity compared to baseline or single-modality models.
Learning a recommender system model from an item's raw modality features (such as image, text, audio, etc.), called MoRec, has attracted growing interest recently. One key advantage of MoRec is that it can easily benefit from advances in other fields, such as natural language processing (NLP) and computer vision (CV). Moreover, it naturally supports transfer learning across different systems through modality features, known as transferable recommender systems, or TransRec. However, so far, TransRec has made little progress, compared to groundbreaking foundation models in the fields of NLP and CV. The lack of large-scale, high-quality recommendation datasets poses a major obstacle. To this end, we introduce NineRec, a TransRec dataset suite that includes a large-scale source domain recommendation dataset and nine diverse target domain recommendation datasets. Each item in NineRec is represented by a text description and a high-resolution cover image. With NineRec, we can implement TransRec models in an end-to-end training manner instead of using pre-extracted invariant features. We conduct a benchmark study and empirical analysis of TransRec using NineRec, and our findings provide several valuable insights. To support further research, we make our code, datasets, benchmarks, and leaderboards publicly available at https://github.com/anonymous?ninerec/NineRec.
In end-to-end automatic speech recognition system, one of the difficulties for language expansion is the limited paired speech and text training data. In this paper, we propose a novel method to generate augmented samples with unpaired speech feature segments and text data for model pre-training, which has the advantage of low cost without using additional speech data. When mixing 20,000 hours augmented speech data generated by our method with 12,500 hours original transcribed speech data for Italian Transformer transducer model pre-training, we achieve 8.7% relative word error rate reduction. The pre-trained model achieves similar performance as the model pre-trained with multilingual transcribed 75,000 hours raw speech data. When merging the augmented speech data with the multilingual data to pre-train a new model, we achieve even more relative word error rate reduction of 12.2% over the baseline, which further verifies the effectiveness of our method for speech data augmentation.
This paper investigates the effectiveness of token-level text augmentation and the role of probabilistic linguistic knowledge within a linguistically-motivated evaluation context. Two text augmentation programs, REDA and REDA$_{NG}$, were developed, both implementing five token-level text editing operations: Synonym Replacement (SR), Random Swap (RS), Random Insertion (RI), Random Deletion (RD), and Random Mix (RM). REDA$_{NG}$ leverages pretrained $n$-gram language models to select the most likely augmented texts from REDA's output. Comprehensive and fine-grained experiments were conducted on a binary question matching classification task in both Chinese and English. The results strongly refute the general effectiveness of the five token-level text augmentation techniques under investigation, whether applied together or separately, and irrespective of various common classification model types used, including transformers. Furthermore, the role of probabilistic linguistic knowledge is found to be minimal.
We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Reality experiences using LLMs. LLMR leverages novel strategies to tackle difficult cases where ideal training data is scarce, or where the design goal requires the synthesis of internal dynamics, intuitive analysis, or advanced interactivity. Our framework relies on text interaction and the Unity game engine. By incorporating techniques for scene understanding, task planning, self-debugging, and memory management, LLMR outperforms the standard GPT-4 by 4x in average error rate. We demonstrate LLMR's cross-platform interoperability with several example worlds, and evaluate it on a variety of creation and modification tasks to show that it can produce and edit diverse objects, tools, and scenes. Finally, we conducted a usability study (N=11) with a diverse set that revealed participants had positive experiences with the system and would use it again.
The rapid evolution of Multi-modality Large Language Models (MLLMs) has catalyzed a shift in computer vision from specialized models to general-purpose foundation models. Nevertheless, there is still an inadequacy in assessing the abilities of MLLMs on low-level visual perception and understanding. To address this gap, we present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment. a) To evaluate the low-level perception ability, we construct the LLVisionQA dataset, consisting of 2,990 diverse-sourced images, each equipped with a human-asked question focusing on its low-level attributes. We then measure the correctness of MLLMs on answering these questions. b) To examine the description ability of MLLMs on low-level information, we propose the LLDescribe dataset consisting of long expert-labelled golden low-level text descriptions on 499 images, and a GPT-involved comparison pipeline between outputs of MLLMs and the golden descriptions. c) Besides these two tasks, we further measure their visual quality assessment ability to align with human opinion scores. Specifically, we design a softmax-based strategy that enables MLLMs to predict quantifiable quality scores, and evaluate them on various existing image quality assessment (IQA) datasets. Our evaluation across the three abilities confirms that MLLMs possess preliminary low-level visual skills. However, these skills are still unstable and relatively imprecise, indicating the need for specific enhancements on MLLMs towards these abilities. We hope that our benchmark can encourage the research community to delve deeper to discover and enhance these untapped potentials of MLLMs. Project Page: https://vqassessment.github.io/Q-Bench.
Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of $3,222$ driving videos collected from multiple countries, annotated with $10,500$ questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa
Combining computational technologies and humanities is an ongoing effort aimed at making resources such as texts, images, audio, video, and other artifacts digitally available, searchable, and analyzable. In recent years, deep neural networks (DNN) dominate the field of automatic text analysis and natural language processing (NLP), in some cases presenting a super-human performance. DNNs are the state-of-the-art machine learning algorithms solving many NLP tasks that are relevant for Digital Humanities (DH) research, such as spell checking, language detection, entity extraction, author detection, question answering, and other tasks. These supervised algorithms learn patterns from a large number of "right" and "wrong" examples and apply them to new examples. However, using DNNs for analyzing the text resources in DH research presents two main challenges: (un)availability of training data and a need for domain adaptation. This paper explores these challenges by analyzing multiple use-cases of DH studies in recent literature and their possible solutions and lays out a practical decision model for DH experts for when and how to choose the appropriate deep learning approaches for their research. Moreover, in this paper, we aim to raise awareness of the benefits of utilizing deep learning models in the DH community.
Fusing multi-modal data can improve the performance of deep learning models. However, missing modalities are common for medical data due to patients' specificity, which is detrimental to the performance of multi-modal models in applications. Therefore, it is critical to adapt the models to missing modalities. This study aimed to develop an efficient multi-modal fusion architecture for medical data that was robust to missing modalities and further improved the performance on disease diagnosis.X-ray chest radiographs for the image modality, radiology reports for the text modality, and structured value data for the tabular data modality were fused in this study. Each modality pair was fused with a Transformer-based bi-modal fusion module, and the three bi-modal fusion modules were then combined into a tri-modal fusion framework. Additionally, multivariate loss functions were introduced into the training process to improve model's robustness to missing modalities in the inference process. Finally, we designed comparison and ablation experiments for validating the effectiveness of the fusion, the robustness to missing modalities and the enhancements from each key component. Experiments were conducted on MIMIC-IV, MIMIC-CXR with the 14-label disease diagnosis task. Areas under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC) were used to evaluate models' performance. The experimental results demonstrated that our proposed multi-modal fusion architecture effectively fused three modalities and showed strong robustness to missing modalities. This method is hopeful to be scaled to more modalities to enhance the clinical practicality of the model.
Multimodal transfer learning aims to transform pretrained representations of diverse modalities into a common domain space for effective multimodal fusion. However, conventional systems are typically built on the assumption that all modalities exist, and the lack of modalities always leads to poor inference performance. Furthermore, extracting pretrained embeddings for all modalities is computationally inefficient for inference. In this work, to achieve high efficiency-performance multimodal transfer learning, we propose VideoAdviser, a video knowledge distillation method to transfer multimodal knowledge of video-enhanced prompts from a multimodal fundamental model (teacher) to a specific modal fundamental model (student). With an intuition that the best learning performance comes with professional advisers and smart students, we use a CLIP-based teacher model to provide expressive multimodal knowledge supervision signals to a RoBERTa-based student model via optimizing a step-distillation objective loss -- first step: the teacher distills multimodal knowledge of video-enhanced prompts from classification logits to a regression logit -- second step: the multimodal knowledge is distilled from the regression logit of the teacher to the student. We evaluate our method in two challenging multimodal tasks: video-level sentiment analysis (MOSI and MOSEI datasets) and audio-visual retrieval (VEGAS dataset). The student (requiring only the text modality as input) achieves an MAE score improvement of up to 12.3% for MOSI and MOSEI. Our method further enhances the state-of-the-art method by 3.4% mAP score for VEGAS without additional computations for inference. These results suggest the strengths of our method for achieving high efficiency-performance multimodal transfer learning.