Related papers: Modeling Layout Reading Order as Ordering Relation…
Markov decision processes capture sequential decision making under uncertainty, where an agent must choose actions so as to optimize long term reward. The paper studies efficient reasoning mechanisms for Relational Markov Decision Processes…
Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, large-scale pre-training approaches have been developed and…
Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, and structural elements. Recently, Multimodal Large Language…
The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme. Past research in this area has typically focused on one of two approaches to this…
Document layout analysis involves understanding the arrangement of elements within a document. This paper navigates the complexities of understanding various elements within document images, such as text, images, tables, and headings. The…
Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…
Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training. However, the importance of layout structure (i.e., the spatial relationship between the entity…
Graphs are often used to model relationships between entities. The identification and visualization of clusters in graphs enable insight discovery in many application areas, such as life sciences and social sciences. Force-directed graph…
This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application…
Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically,…
While Vision-Language Models (VLMs) enable high-level semantic reasoning for end-to-end autonomous driving, particularly in unstructured environments, existing off-road datasets suffer from language annotations that are weakly aligned with…
Discontinuity layout optimization (DLO) is a relatively new upper bound limit analysis method. Compared to classic topology optimization methods, aimed at obtaining the optimum design of a structure by considering its self-weight, building…
Document expansion is a classical technique for improving retrieval quality, and is attractive since it shifts computation offline, avoiding additional query-time processing. However, when applied to modern retrievers, it has been shown to…
Recently, pre-trained language models such as BERT have been applied to document ranking for information retrieval, which first pre-train a general language model on an unlabeled large corpus and then conduct ranking-specific fine-tuning on…
Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study various phenomena in natural language,…
Conducting a systematic review (SR) is comprised of multiple tasks: (i) collect documents (studies) that are likely to be relevant from digital libraries (eg., PubMed), (ii) manually read and label the documents as relevant or irrelevant,…
Information extraction (IE) has been studied extensively. The existing methods always follow a fixed extraction order for complex IE tasks with multiple elements to be extracted in one instance such as event extraction. However, we conduct…
Document layout analysis is a key area in document research, involving techniques like text mining and visual analysis. Despite various methods developed to tackle layout analysis, a critical but frequently overlooked problem is the…
Visual Odometry (VO) is essential to downstream mobile robotics and augmented/virtual reality tasks. Despite recent advances, existing VO methods still rely on heuristic design choices that require several weeks of hyperparameter tuning by…
Detailed routing remains one of the most complex and time-consuming steps in modern physical design due to the challenges posed by shrinking feature sizes and stricter design rules. Prior detailed routers achieve state-of-the-art results by…