paper-with-me

홈 › Papers

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings

2026-04-21 · Zijie Li, Yichun Shi, Jingxiang Sun, Ye Wang, Yixuan Huang, Zhiyao Guo, Xiaochen Lian, Peihao Zhu, Yu Tian, Zhonghua Zhai, Peng Wang arxiv

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 serve as conditioning signals for a diffusion model. This streamlined design effectively transfers the rich understanding and reasoning capabilities of VLMs into the visual generation process. By obviating the need for deep fusion between autoregressive and diffusion models or training from scratch, MMCORE significantly reduces computational overhead while maintaining high-fidelity synthesis. MMCORE seamlessly integrates text-to-image synthesis with interleaved image generation, demonstrating robust multimodal comprehension in complex scenarios such as spatial reasoning and visual grounding. Comprehensive evaluations indicate that MMCORE consistently outperforms state-of-the-art baselines across a broad spectrum of text-to-image and single/multi-image editing benchmarks.

📄 PDF Abstract BibTeX arXiv:2604.19902

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial ReasoningVisual GroundingImage GenerationImage Editing

Similar Papers 제목 키워드 기반

Calibrated Multimodal Representation Learning with Missing Modalities

2025-11-15 · Xiaohao Liu, Xiaobo Xia, Jiaheng Wei, Shuo Yang 외 arxiv

Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but req…

Representation Learning

Multimodal LLMs under Pairwise Modalities

2026-05-20 · Yan Li, Yunlong Deng, Yuewen Sun, Gongxu Luo 외 arxiv

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned d…

Representation LearningContrastive LearningPoint Clouds

Latent-Aligned Reasoning for Multimodal Recommendation

2026-09-04 · Jiarui Jin, Anyang Ji arxiv

Multimodal Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding, yet a fundamental challenge persists when applying them to recommendation: as representations propagate thr…

Multimodal RecommendationContrastive Learning

Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

2026-06-23 · Wangyi Pu, Michele Scarpiniti arxiv

Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment. Flow Matching offer…

Speech Enhancement

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

2024-06-22 · Lorenzo Basile, Santiago Acevedo, Luca Bortolussi, Fabio Anselmi 외

To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations often exhibit a high-dimensional and stro…