相关论文: EdiVal-Agent: An Object-Centric Framework for Auto…

Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while…

There is a high demand for audio-visual editing in video post-production and the film making field. While numerous models have explored audio and video editing, they struggle with object-level audio-visual operations. Specifically,…

By comparing the original and target prompts, we can obtain numerous editing pairs, each comprising an object and its corresponding editing target. To allow editability while maintaining fidelity to the input image, existing editing methods…

To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to…

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…

The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators…

With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on…

Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…

In this paper, we focus on the task of instruction-based image editing. Previous works like InstructPix2Pix, InstructDiffusion, and SmartEdit have explored end-to-end editing. However, two limitations still remain: First, existing datasets…

The rapid development of diffusion models has significantly advanced AI-generated content (AIGC), particularly in Text-to-Image (T2I) and Text-to-Video (T2V) generation. Text-based video editing, leveraging these generative capabilities,…

Affective Image Manipulation (AIM) aims to alter visual elements within an image to evoke specific emotional responses from viewers. However, existing AIM approaches rely on rigid \emph{one-to-one} mappings between emotions and visual cues,…

Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the…

Evaluating text-to-vision content hinges on two crucial aspects: visual quality and alignment. While significant progress has been made in developing objective models to assess these dimensions, the performance of such models heavily relies…

Instruction-based image editing (IIE) aims to modify images according to textual instructions while preserving irrelevant content. Despite recent advances in diffusion transformers, existing methods often suffer from over-editing,…

Recent advances in AI-generated content (AIGC) have significantly accelerated image editing techniques, driving increasing demand for diverse and fine-grained edits. Despite these advances, existing image editing methods still face…

In embodied AI, visual perception should be active rather than passive: the system must decide where to look and at what scale to sense to acquire maximally informative data under pixel and spatial budget constraints. Existing vision models…

The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…

Improving vision-language models (VLMs) in the post-training stage typically relies on supervised fine-tuning or reinforcement learning, methods that necessitate costly, human-annotated data. While self-supervised techniques have proven…

Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce…

Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL…