相关论文: When to Lock Attention: Training-Free KV Control i…

In vision-language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations. This issue becomes particularly severe in dense prediction tasks such as spatial-temporal video grounding…

Rapid advancements in video diffusion models have enabled the creation of realistic videos, raising concerns about unauthorized use and driving the demand for techniques to protect model ownership. Existing watermarking methods, while…

CLIP-based prompt tuning enables pretrained Vision-Language Models (VLMs) to efficiently adapt to downstream tasks. Although existing studies have made significant progress, they pay limited attention to changes in the internal attention…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Recently, video diffusion models (VDMs) have garnered significant attention due to their notable advancements in generating coherent and realistic video content. However, processing multiple frame features concurrently, coupled with the…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attributes, actions, and motion directions. We hypothesize that…

Video Quality Assessment (VQA), which intends to predict the perceptual quality of videos, has attracted increasing attention. Due to factors like motion blur or specific distortions, the quality of different regions in a video varies.…

Diffusion-based visuomotor policies built on 3D visual representations have achieved strong performance in learning complex robotic skills. However, most existing methods employ an oversized denoising decoder. While increasing model…

Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. However, these attributions also hinder the practical deployment…

Large vision-language models (LVLMs) have made substantial progress in integrating large language models (LLMs) with visual inputs, enabling advanced multimodal reasoning. Despite their success, a persistent challenge is hallucination-where…

Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges in maintaining fidelity and temporal consistency. Existing…

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity…

Contrastive decoding strategies are widely used to mitigate object hallucinations in multimodal large language models (MLLMs). By reducing over-reliance on language priors, these strategies ensure that generated content remains closely…

Zero-shot, training-free, image-based text-to-video generation is an emerging area that aims to generate videos using existing image-based diffusion models. Current methods in this space require specific architectural changes to image…

We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional…

Layout generation is a foundation task of graphic design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually…

This paper presents Qffusion, a dual-frame-guided framework for portrait video editing. Specifically, we consider a design principle of ``animation for editing'', and train Qffusion as a general animation framework from two still reference…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Object-level manipulation, relocating or reorienting objects in images or videos while preserving scene realism, is central to film post-production, AR, and creative editing. Yet existing methods struggle to jointly achieve three core…