Related papers: Multimodal Reranking for Knowledge-Intensive Visua…

Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the…

Knowledge-based visual question answering (KB-VQA) requires visual language models (VLMs) to integrate visual understanding with external knowledge retrieval. Although retrieval-augmented generation (RAG) achieves significant advances in…

Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods…

We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair.…

Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate relevant evidence across interleaved text and images. Prior…

Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG) over long documents. While recent VLM-based rerankers achieve strong accuracy, their…

Knowledge-based Visual Question Answering about Named Entities is a challenging task that requires retrieving information from a multimodal Knowledge Base. Named entities have diverse visual representations and are therefore difficult to…

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA). However, even state-of-the-art MLLMs struggle with…

Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "retrieve-then-answer" pipelines often suffer from cascading…

Question Answering (QA) systems have traditionally relied on structured text data, but the rapid growth of multimedia content (images, audio, video, and structured metadata) has introduced new challenges and opportunities for…

In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker.…

Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions with knowledge retrieved from external knowledge bases. The tasks of knowledge retrieval and answer generation tasks both necessitate…

Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face…

Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers. Existing approaches typically adopt the rerank-then-read framework, where a reader reads top-ranking evidence to predict answers. According…

Knowledge-based Visual Question Answering (KB-VQA) requires models to answer questions by integrating visual information with external knowledge. However, retrieved knowledge is often noisy, partially irrelevant, or misaligned with the…

The existing methods for image search reranking suffer from the unfaithfulness of the assumptions under which the text-based images search result. The resulting images contain more irrelevant images. Hence the re ranking concept arises to…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in processing and generating content across multiple data modalities. However, a significant drawback of MLLMs is their reliance on static training data,…

This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). We design a novel…

Visual Question Answering systems face reliability issues due to hallucinations, where models generate answers misaligned with visual input or factual knowledge. While Retrieval Augmented Generation frameworks mitigate this issue by…