Related papers: Multimodal UNcommonsense: From Odd to Ordinary and…

There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from multimodal training.…

We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (MLLMs). MLLMs are trained to represent vision and language in…

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in…

In this report, we present OpenUni, a simple, lightweight, and fully open-source baseline for unifying multimodal understanding and generation. Inspired by prevailing practices in unified model learning, we adopt an efficient training…

Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remains underexplored. We investigate MLLMs as training-free similarity estimators for…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal…

In-context learning (ICL) enhances the reasoning abilities of Large Language Models (LLMs) by prepending a few demonstrations. It motivates researchers to introduce more examples to provide additional contextual information for the…

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use…

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE)…

We introduce UEval, a benchmark to evaluate unified models, i.e., models capable of generating both images and text. UEval comprises 1,000 expert-curated questions that require both images and text in the model output, sourced from 8…

Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in…

Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key…

In this paper, we address the task of utterance level emotion recognition in conversations using commonsense knowledge. We propose COSMIC, a new framework that incorporates different elements of commonsense such as mental states, events,…

Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and…

The digital landscape continually evolves with multimodality, enriching the online experience for users. Creators and marketers aim to weave subtle contextual cues from various modalities into congruent content to engage users with a…

Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair. Existing retrieval-augmented approaches mainly focused on modeling the…

Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring…

The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alignment with human values. While extensive research has addressed moral evaluation in LLMs,…

Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that…