相关论文: Wan-Weaver: Interleaved Multi-modal Generation via…

Interleaved image-text generation has emerged as a crucial multimodal task, aiming at creating sequences of interleaved visual and textual content given a query. Despite notable advancements in recent multimodal large language models…

Multimodal learning for generative models often refers to the learning of abstract concepts from the commonality of information in multiple modalities, such as vision and language. While it has proven effective for learning generalisable…

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at…

In complex embodied long-horizon manipulation tasks, effective task decomposition and execution require synergistic integration of textual logical reasoning and visual-spatial imagination to ensure efficient and accurate operation. Current…

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…

Many self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.…

Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not…

While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing…

This work investigates a challenging task named open-domain interleaved image-text generation, which generates interleaved texts and images following an input query. We propose a new interleaved generation framework based on prompting…

We propose LLM-Interleaved (LLM-I), a flexible and dynamic framework that reframes interleaved image-text generation as a tool-use problem. LLM-I is designed to overcome the "one-tool" bottleneck of current unified models, which are limited…

Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed…

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and…

Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about what should happen next. In this paper, we introduce a new…

The effectiveness of Multimodal Large Language Models (MLLMs) demonstrates a profound capability in multimodal understanding. However, the simultaneous generation of images with coherent texts is still underdeveloped. Addressing this, we…

Multimodal data are prevalent across various domains, and learning robust representations of such data is paramount to enhancing generation quality and downstream task performance. To handle heterogeneity and interconnections among…

We propose an efficient method to ground pretrained text-only language models to the visual domain, enabling them to process arbitrarily interleaved image-and-text data, and generate text interleaved with retrieved images. Our method…

Multimodal learning is a framework for building models that make predictions based on different types of modalities. Important challenges in multimodal learning are the inference of shared representations from arbitrary modalities and…

People get informed of a daily task plan through diverse media involving both texts and images. However, most prior research only focuses on LLM's capability of textual plan generation. The potential of large-scale models in providing…