相关论文: FlexMUSE: Multimodal Unification and Semantics Enh…

Existing text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images guided by textual prompts. However, achieving multi-subject compositional synthesis with precise spatial control remains a…

Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality…

Generating long-form audio-visual stories from a short user prompt remains challenging due to an intent-execution gap, where high-level narrative intent must be preserved across coherent, shot-level multimodal generation over long horizons.…

Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on…

Multimodal semantic segmentation shows significant potential for enhancing segmentation accuracy in complex scenes. However, current methods often incorporate specialized feature fusion modules tailored to specific modalities, thereby…

Multimodal entity linking (MEL) task, which aims at resolving ambiguous mentions to a multimodal knowledge graph, has attracted wide attention in recent years. Though large efforts have been made to explore the complementary effect among…

In this work, we introduce FlexGen, a flexible framework designed to generate controllable and consistent multi-view images, conditioned on a single-view image, or a text prompt, or both. FlexGen tackles the challenges of controllable…

Generative recommendation has recently emerged as a powerful paradigm that unifies retrieval and generation, representing items as discrete semantic tokens and enabling flexible sequence modeling with autoregressive models. Despite its…

Advanced image fusion methods are devoted to generating the fusion results by aggregating the complementary information conveyed by the source images. However, the difference in the source-specific manifestation of the imaged scene content…

Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text has not been fully studied. In this work, we propose…

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity…

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality…

Voice, the discursive construction of the writer's identity, has been extensively studied and theorized in composition studies. In multimodal writing, students are able to mobilize both linguistic and non linguistic resources to express…

Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing…

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently…

Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization…

Multimodal learning has gained increasing importance across various fields, offering the ability to integrate data from diverse sources such as images, text, and personalized records, which are frequently observed in medical domains.…

This paper extends Cross Modal Generalization (CMG) to open-set environments by proposing the more challenging Open-set Cross Modal Generalization (OSCMG) task. This task evaluates multimodal unified representations in open-set conditions,…

Multimodal Sentiment Analysis (MSA) with missing modalities has attracted increasing attention recently. While current Transformer-based methods leverage dense text information to maintain model robustness, their quadratic complexity…

Image captioning model is a cross-modality knowledge discovery task, which targets at automatically describing an image with an informative and coherent sentence. To generate the captions, the previous encoder-decoder frameworks directly…