Related papers: Bernini: Latent Semantic Planning for Video Diffus…
In-context segmentation has drawn increasing attention with the advent of vision foundation models. Its goal is to segment objects using given reference images. Most existing approaches adopt metric learning or masked image modeling to…
Multimodal Recommender Systems aim to improve recommendation accuracy by integrating heterogeneous content, such as images and textual metadata. While effective, it remains unclear whether their gains stem from true multimodal understanding…
Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g.,…
Humans possess the capability to comprehend diverse modalities and seamlessly transfer information between them. In this work, we introduce ModaVerse, a Multi-modal Large Language Model (MLLM) capable of comprehending and transforming…
Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the…
While latent diffusion models (LDMs), such as Stable Diffusion, are designed for high-resolution (HR) image generation, they often struggle with significant structural distortions when generating images at resolutions higher than their…
Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode text and reference images separately. This limits…
Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context…
Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into…
Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…
Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and textual modalities…
Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP). The two most common architectures are encoders such as BERT, and decoders like the GPT models. Despite the success of encoder…
Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. While MLLMs demonstrate remarkable versatility, MLLMs appears limited…
Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel…
We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, "visual sentences", in which we can represent raw images…
The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual question answering, we design a 2x2 experimental framework to…
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…
Recently, diffusion models have excelled in image generation tasks and have also been applied to neural language processing (NLP) for controllable text generation. However, the application of diffusion models in a cross-lingual setting is…
Recent diffusion-based image editing methods have significantly advanced text-guided tasks but often struggle to interpret complex, indirect instructions. Moreover, current models frequently suffer from poor identity preservation,…
Text-to-image diffusion models have achieved remarkable image quality, but they still struggle with complex, multiele ment prompts, and limited stylistic diversity. To address these limitations, we propose a Multi-Expert Planning and Gen…