paper-with-me

Papers

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

2024-09-06 · Yecheng Wu, Zhuoyang Zhang, Junyu Chen, Haotian Tang, Dacheng Li, Yunhao Fang, Ligeng Zhu, Enze Xie, Hongxu Yin, Li Yi, Song Han, Yao Lu

VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to misalignment and increased complexity. In contrast, VILA-U employs a single autoregressive next-token prediction framework for both tasks, eliminating the need for additional components like diffusion models. This approach not only simplifies the model but also achieves near state-of-the-art performance in visual language understanding and generation. The success of VILA-U is attributed to two main factors: the unified vision tower that aligns discrete visual tokens with textual inputs during pretraining, which enhances visual perception, and autoregressive image generation can achieve similar quality as diffusion models with high-quality dataset. This allows VILA-U to perform comparably to more complex models using a fully token-based autoregressive framework.

📄 PDF Abstract BibTeX arXiv:2409.04429

Code (1)

mit-han-lab/vila-u 공식 구현 pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

2025-10-20 · Samir Khaki, Junxian Guo, Jiaming Tang, Shang Yang 외 arxiv

Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analysis, and multi-turn conversation. However…

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

2024-08-19 · Yukang Chen, Fuzhao Xue, Dacheng Li, Qinghao Hu 외

Long-context capability is critical for multi-modal foundation models, especially for long video understanding. We introduce LongVILA, a full-stack solution for long-context visual-language models by co-designing the alg…

Video CaptioningVideo Question AnsweringVideo Understanding

ViLA: Efficient Video-Language Alignment for Video Question Answering

2023-12-13 · Xijun Wang, Junbang Liang, Chun-Kai Wang, Kenan Deng 외

In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a…

cross-modal alignmentLanguage ModelingLanguage ModellingQuestion Answering+3

Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning

2023-11-29 · Yingdong Hu, Fanqi Lin, Tong Zhang, Li Yi 외

In this study, we are interested in imbuing robots with the capability of physically-grounded task planning. Recent advancements have shown that large language models (LLMs) possess extensive knowledge useful in robotic …

Task Planning

X-VILA: Cross-Modality Alignment for Large Language Model

2024-05-29 · Hanrong Ye, De-An Huang, Yao Lu, Zhiding Yu 외

We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs …

Instruction FollowingLanguage ModelingLanguage ModellingLarge Language Model