Related papers: DMAP: Human-Aligned Structural Document Map for Mu…
Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark…
Establishing stable mappings between natural language expressions and visual percepts is a foundational problem for both cognitive science and artificial intelligence. Humans routinely ground linguistic reference in noisy, ambiguous…
Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions…
Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current approaches struggle to decompose intricate questions into…
Recent methods for customizing Large Vision Language Models (LVLMs) for domain-specific tasks have shown promising results in scientific chart comprehension. However, existing approaches face two major limitations: First, they rely on…
Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the application scenario of retrieving…
The abundant semi-structured data on the Web, such as HTML-based tables and lists, provide commercial search engines a rich information source for question answering (QA). Different from plain text passages in Web documents, Web tables and…
When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged in recent years, there has been…
Document understanding aims to perform question answering and information extraction over document images, where the visual content is highly information-dense and most queries rely on only a few relevant layout regions. However, existing…
Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and…
Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes…
A structured understanding of intraoral 3D scans is essential for digital orthodontics. However, existing deep-learning approaches rely heavily on modality-specific training, large annotated datasets, and controlled scanning conditions,…
Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex reasoning, leading to hallucinations and unreliable…
Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in…
We propose DocVXQA, a novel framework for visually self-explainable document question answering. The framework is designed not only to produce accurate answers to questions but also to learn visual heatmaps that highlight contextually…
Despite significant progress in multimodal large language models (MLLMs), their performance on complex, multi-page document comprehension remains inadequate, largely due to the lack of high-quality, document-level datasets. While current…
Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in…
Reducing hallucination of Large Language Models (LLMs) is imperative for use in the sciences, where reliability and reproducibility are crucial. However, LLMs inherently lack long-term memory, making it a nontrivial, ad hoc, and inevitably…
Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer, rather than only the region containing the final response. Creating such…
In this paper, we study the problem of numerical multi-table question answering (MTQA) over large-scale table collections (e.g., online data repositories). This task is essential in many analytical applications. Existing MTQA solutions,…