Related papers: Progressive Multimodal Search and Reasoning for Kn…
Recently, Large Language Models (LLMs) have been used for knowledge-based Visual Question Answering (VQA). Despite the encouraging results of previous studies, prior methods prompt LLMs to predict answers directly, neglecting intermediate…
Knowledge-Based Visual Question Answering (KB-VQA) methods focus on tasks that demand reasoning with information extending beyond the explicit content depicted in the image. Early methods relied on explicit knowledge bases to provide this…
Visual Question Answering is a multi-modal task that aims to measure high-level visual understanding. Contemporary VQA models are restrictive in the sense that answers are obtained via classification over a limited vocabulary (in the case…
Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing…
Fact-based Visual Question Answering (FVQA) requires external knowledge beyond visible content to answer questions about an image, which is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is…
Retrieval-augmented generation (RAG) enables large language models (LLMs) to dynamically access external information, which is powerful for answering questions over previously unseen documents. Nonetheless, they struggle with high-level…
Explanation and high-order reasoning capabilities are crucial for real-world visual question answering with diverse levels of inference complexity (e.g., what is the dog that is near the girl playing with?) and important for users to…
Visual Question Answering (VQA) is an interdisciplinary field that bridges the gap between computer vision (CV) and natural language processing(NLP), enabling Artificial Intelligence(AI) systems to answer questions about images. Since its…
Knowledge-based Visual Question Answering (KVQA) tasks require answering questions about images using extensive background knowledge. Despite significant advancements, generative models often struggle with these tasks due to the limited…
Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only…
Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge…
Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such scenes, task-critical evidence is often carried by small objects, explicit quantities,…
Accurate diagnosis of ophthalmic diseases relies heavily on the interpretation of multimodal ophthalmic images, a process often time-consuming and expertise-dependent. Visual Question Answering (VQA) presents a potential interdisciplinary…
In this paper, we propose a new dataset, ReasonVQA, for the Visual Question Answering (VQA) task. Our dataset is automatically integrated with structured encyclopedic knowledge and constructed using a low-cost framework, which is capable of…
Protein analysis tasks arising in healthcare settings often require accurate reasoning under protein sequence constraints, involving tasks such as functional interpretation of disease-related variants, protein-level analysis for clinical…
Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task's inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs)…
The emergence of Multimodal Large Language Models (MLLMs) that integrate vision and language modalities has unlocked new potentials for scientific reasoning, outperforming prior benchmarks in both natural language and coding domains.…
Scientific reasoning is a key aspect of human intelligence, requiring the integration of multimodal inputs, domain expertise, and multi-step inference across various subjects. Existing benchmarks for multimodal large language models (MLLMs)…
Multimodal information, together with our knowledge, help us to understand the complex and dynamic world. Large language models (LLM) and large multimodal models (LMM), however, still struggle to emulate this capability. In this paper, we…
Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…