Related papers: MiLDEdit: Reasoning-Based Multi-Layer Design Docum…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
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…
Molecular editing and optimization are multi-step problems that require iteratively improving properties while keeping molecules chemically valid and structurally similar. We frame both tasks as sequential, tool-guided decisions and…
Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex…
While Multimodal Large Language Models (MLLMs) perform strongly on single-turn chart generation, their ability to support real-world exploratory data analysis remains underexplored. In practice, users iteratively refine visualizations…
Instruction-based image editing has garnered significant attention due to its direct interaction with users. However, real-world user instructions are immensely diverse, and existing methods often fail to generalize effectively to…
Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…
Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered…
Recent advancements in image editing have utilized large-scale multimodal models to enable intuitive, natural instruction-driven interactions. However, conventional methods still face significant challenges, particularly in spatial…
Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity of real-world problems, which demand open-ended,…
Generating academic slides from scientific papers is a challenging multimodal reasoning task that requires both long context understanding and deliberate visual planning. Existing approaches largely reduce it to text only summarization,…
While foundation models (FMs), such as diffusion models and large vision-language models (LVLMs), have been widely applied in educational contexts, their ability to generate pedagogically effective visual explanations remains limited. Most…
Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive pipelines. We…
LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents, which demand strong reasoning and planning abilities. Nevertheless, existing benchmarks mostly assess their reasoning abilities in…
Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during…
Recent progress in Multi-modal Large Language Models (MLLMs) has enabled step-by-step multi-modal mathematical reasoning by performing visual operations based on the textual instructions. A promising approach uses code as an intermediate…
Multi-agent systems built upon large language models (LLMs) have demonstrated remarkable capabilities in tackling complex compositional tasks. In this work, we apply this paradigm to the paper-to-poster generation problem, a practical yet…
Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs…
Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense reasoning, offering limited assessment of this capability…
Spreadsheets are ubiquitous across the World Wide Web, playing a critical role in enhancing work efficiency across various domains. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has not…