Related papers: Reasoning to Align: Implicit Reasoning in Diffusio…
Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on…
Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating high-fidelity visuals, text-to-image models can still struggle…
Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency. By inserting small, learnable modules into pretrained…
Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with…
Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. It is widely studied in recent years as a promising and challenging field of Artificial Intelligence Generative Content (AIGC).…
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…
Large-scale video diffusion models show strong world simulation and temporal reasoning abilities, but their use as zero-shot image editors remains underexplored. We introduce IF-Edit, a tuning-free framework that repurposes pretrained…
In this paper, we present CCEdit, a versatile generative video editing framework based on diffusion models. Our approach employs a novel trident network structure that separates structure and appearance control, ensuring precise and…
Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this…
Reasoning about visual relationships is central to how humans interpret the visual world. This task remains challenging for current deep learning algorithms since it requires addressing three key technical problems jointly: 1) identifying…
Diffusion-based \textit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional conditions, into a temporally coherent video. Compared with broader video generation…
Text-guided image editing on real or synthetic images, given only the original image itself and the target text prompt as inputs, is a very general and challenging task. It requires an editing model to estimate by itself which part of the…
Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video generation, which offers broader applications, remains…
Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference…
Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate…
Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present…
Scene text editing aims to modify text in a target region of an image while preserving surrounding background style and texture. Existing methods rely solely on image background information while neglecting the visual details of target…
Text-to-image synthesis aims to generate natural images conditioned on text descriptions. The main difficulty of this task lies in effectively fusing text information into the image synthesis process. Existing methods usually adaptively…
Diffusion models continuously push the boundary of state-of-the-art image generation, but the process is hard to control with any nuance: practice proves that textual prompts are inadequate for accurately describing image style or fine…
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…