Related papers: GLANCE: A Global-Local Coordination Multi-Agent Fr…
Real-world design documents (e.g., posters) are inherently multi-layered, combining decoration, text, and images. Editing them from natural-language instructions requires fine-grained, layer-aware reasoning to identify relevant layers and…
We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation,…
Low-light image enhancement remains a challenging problem due to severe noise, color distortion, contrast degradation, and loss of structural details under insufficient illumination. Existing methods typically apply uniform enhancement…
Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories:…
Generating step-by-step "how-to" procedures is a key LLM capability: how-to advice is commonly requested in chatbots, and step-by-step planning is critical for reasoning over complex tasks. Yet, measuring and improving procedural validity…
Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…
The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available,…
In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while…
The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts.…
Current vision-guided audio captioning systems frequently fail to address audiovisual misalignment in real-world scenarios, such as dubbed content or off-screen sounds. To bridge this critical gap, we present an entropy-aware gated fusion…
Large language model (LLM) agents have demonstrated strong capabilities in long-horizon tasks by interleaving reasoning with tool use. However, as these agents scale to complex workflows such as software engineering and open-ended research,…
Music-to-dance generation represents a challenging yet pivotal task at the intersection of choreography, virtual reality, and creative content generation. Despite its significance, existing methods face substantial limitation in achieving…
This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there are currently no…
Recent advances in image-text pretraining have significantly enhanced visual understanding by aligning visual and textual representations. Contrastive Language-Image Pretraining (CLIP) has played a pivotal role in multimodal learning.…
Data augmentation with \textbf{Mixup} has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels at once through linear interpolation. However, this one-stage…
Despite the remarkable progress in text-driven video editing, generating coherent non-rigid deformations remains a critical challenge, often plagued by physical distortion and temporal flicker. To bridge this gap, we propose NRVBench, the…
Video creation has become increasingly popular, yet the expertise and effort required for editing often pose barriers to beginners. In this paper, we explore the integration of large language models (LLMs) into the video editing workflow to…
Environment designers in the entertainment industry create imaginative 2D and 3D scenes for games, films, and television, requiring both fine-grained control of specific details and consistent global coherence. Designers have increasingly…
Creation of images using generative adversarial networks has been widely adapted into multi-modal regime with the advent of multi-modal representation models pre-trained on large corpus. Various modalities sharing a common representation…
MLLMs have been widely studied for video question answering recently. However, most existing assessments focus on natural videos, overlooking synthetic videos, such as AI-generated content (AIGC). Meanwhile, some works in video generation…