Related papers: UnifiedQA-v2: Stronger Generalization via Broader …

We propose a generalized class of multimodal fusion operators for the task of visual question answering (VQA). We identify generalizations of existing multimodal fusion operators based on the Hadamard product, and show that specific…

PDFs are the second-most used document type on the internet (after HTML). Yet, existing QA datasets commonly start from text sources or only address specific domains. In this paper, we present pdfQA, a multi-domain 2K human-annotated…

Question Answering (QA) is key for making possible a robust communication between human and machine. Modern language models used for QA have surpassed the human-performance in several essential tasks; however, these models require large…

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a…

Visual Question Answering (VQA) has been a popular task that combines vision and language, with numerous relevant implementations in literature. Even though there are some attempts that approach explainability and robustness issues in VQA…

Open-domain question answering (QA) is known to involve several underlying knowledge and reasoning challenges, but are models actually learning such knowledge when trained on benchmark tasks? To investigate this, we introduce several new…

Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data…

Table question answering (TQA) focuses on answering questions based on tabular data. Developing TQA systems targets effective interaction with tabular data for tasks such as cell retrieval and data analysis. While recent work has leveraged…

Unified vision large language models (VLLMs) have recently achieved impressive advancements in both multimodal understanding and generation, powering applications such as visual question answering and text-guided image synthesis. However,…

This study uses stacked generalization, which is a two-step process of combining machine learning methods, called meta or super learners, for improving the performance of algorithms in step one (by minimizing the error rate of each…

Vision-and-language (V&L) models pretrained on large-scale multimodal data have demonstrated strong performance on various tasks such as image captioning and visual question answering (VQA). The quality of such models is commonly assessed…

Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to…

The financial domain frequently deals with large numbers of long documents that are essential for daily operations. Significant effort is put towards automating financial data analysis. However, a persistent challenge, not limited to the…

We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn…

Despite the successes of pretrained language models, there are still few high-quality, general-purpose QA systems that are freely available. In response, we present Macaw, a versatile, generative question-answering (QA) system that we are…

The emergence of structured databases for Question Answering (QA) systems has led to developing methods, in which the problem of learning the correct answer efficiently is based on a linking task between the constituents of the question and…

We demonstrate the surprising strength of unimodal baselines in multimodal domains, and make concrete recommendations for best practices in future research. Where existing work often compares against random or majority class baselines, we…

Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where…

Community Question Answering (CQA) has become a primary means for people to acquire knowledge, where people are free to ask questions or submit answers. To enhance the efficiency of the service, similar question identification becomes a…

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational…