Related papers: Re-Align: Structured Reasoning-guided Alignment fo…
In this work, we study the problem of Text-to-Image In-Context Learning (T2I-ICL). While Unified Multimodal LLMs (MLLMs) have advanced rapidly in recent years, they struggle with contextual reasoning in T2I-ICL scenarios. To address this…
Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly…
Recent works have made notable advancements in enhancing unified models for text-to-image generation through the Chain-of-Thought (CoT). However, these reasoning methods separate the processes of understanding and generation, which limits…
Emerging unified editing models have demonstrated strong capabilities in general object editing tasks. However, it remains a significant challenge to perform fine-grained editing in complex multi-entity scenes, particularly those where…
Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding…
The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image forgery detection systems. Existing methods, whether non-LLM-based or LLM-based, exhibit…
Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…
In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…
While recent advances in image editing have enabled impressive visual synthesis capabilities, current methods remain constrained by explicit textual instructions and limited editing operations, lacking deep comprehension of implicit user…
Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbnail of an image simultaneously. While effective, this method generates a large number of…
Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address…
Image editing with natural language has gained significant popularity, yet existing methods struggle with intricate object intersections and fine-grained spatial relationships due to the lack of an explicit reasoning process. While…
Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…
Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges of multimodal conditional generation. However, traditional…
Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal intelligence. However, the community still lacks a rigorous…
Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues…
Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning sequence to arrive at the final answer. However, current…
While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recent latent reasoning methods attempt to mitigate this by…
Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can substantially improve performance on complex reasoning tasks. At the same time, In-Context Learning (ICL) has become an important mechanism…
Sophisticated text-centric forgeries, fueled by rapid AIGC advancements, pose a significant threat to societal security and information authenticity. Current methods for text-centric forgery analysis are often limited to coarse-grained…