相关论文: MUGEN: A Playground for Video-Audio-Text Multimoda…

Multimodal reward models (MRMs) play a crucial role in the training, inference, and evaluation of Large Vision Language Models (LVLMs) by assessing response quality. However, existing benchmarks for evaluating MRMs in the video domain…

Foley audio, critical for enhancing the immersive experience in multimedia content, faces significant challenges in the AI-generated content (AIGC) landscape. Despite advancements in AIGC technologies for text and image generation, the…

While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over complex narratives remains poorly evaluated. Existing summarization benchmarks fragment…

Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and…

The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning…

We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides or text summaries, our method advances beyond these…

We introduce WorldGen, a system that enables the automatic creation of large-scale, interactive 3D worlds directly from text prompts. Our approach transforms natural language descriptions into traversable, fully textured environments that…

Text-to-video generative models convert textual prompts into dynamic visual content, offering wide-ranging applications in film production, gaming, and education. However, their real-world performance often falls short of user expectations.…

Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we…

Responding with multi-modal content has been recognized as an essential capability for an intelligent conversational agent. In this paper, we introduce the MMDialog dataset to better facilitate multi-modal conversation. MMDialog is composed…

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…

Retrieval-augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for understanding of videos is appealing but there are two…

Humans can imagine various atmospheres and settings when listening to music, envisioning movie scenes that complement each piece. For example, slow, melancholic music might evoke scenes of heartbreak, while upbeat melodies suggest…

Multimodal counterfactual reasoning is a vital yet challenging ability for AI systems. It involves predicting the outcomes of hypothetical circumstances based on vision and language inputs, which enables AI models to learn from failures and…

We introduce UniMuMo, a unified multimodal model capable of taking arbitrary text, music, and motion data as input conditions to generate outputs across all three modalities. To address the lack of time-synchronized data, we align unpaired…

Building computer systems that can converse about their visual environment is one of the oldest concerns of research in Artificial Intelligence and Computational Linguistics (see, for example, Winograd's 1972 SHRDLU system). Only recently,…

As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT Reserve, a model that represents videos jointly over time -- through a new training objective that learns from audio,…

We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing benchmarks, our WorldSense has several features:…

Speech Relation Extraction (SpeechRE) aims to extract relation triplets directly from speech. However, existing benchmark datasets rely heavily on synthetic data, lacking sufficient quantity and diversity of real human speech. Moreover,…

Chunking has emerged as a critical technique that enhances generative models by grounding their responses in efficiently segmented knowledge [1]. While initially developed for unimodal (primarily textual) domains, recent advances in…