Related papers: SAIL: Sample-Centric In-Context Learning for Docum…
Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in…
Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to solve the task by developing pre-trained language models…
Intrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream applications such as virtual relighting and scene editing.…
Document-level relation extraction has attracted much attention in recent years. It is usually formulated as a classification problem that predicts relations for all entity pairs in the document. However, previous works indiscriminately…
In recent years, much progress has been made in learning robotic manipulation policies that follow natural language instructions. Such methods typically learn from corpora of robot-language data that was either collected with specific tasks…
Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample…
In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…
Many business documents processed in modern NLP and IR pipelines are visually rich: in addition to text, their semantics can also be captured by visual traits such as layout, format, and fonts. We study the problem of information extraction…
Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting…
Invariance learning methods aim to learn invariant features in the hope that they generalize under distributional shifts. Although many tasks are naturally characterized by continuous domains, current invariance learning techniques…
In-context learning (ICL) has become a classic approach for enabling LLMs to handle various tasks based on a few input-output examples. The effectiveness of ICL heavily relies on the quality of these examples, and previous works which…
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many…
Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain,…
In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA)…
Information Extraction (IE) aims to extract structural knowledge (e.g., entities, relations, events) from natural language texts, which brings challenges to existing methods due to task-specific schemas and complex text expressions. Code,…
Information extraction (IE) is a fundamental area in natural language processing where prompting large language models (LLMs), even with in-context examples, cannot defeat small LMs tuned on very small IE datasets. We observe that IE tasks,…
As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-resource, budget-constrained settings? While large VLMs offer…
Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…
In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues:…
Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored.…