Related papers: Webscraper: Leverage Multimodal Large Language Mod…
Multimodal Large Language Models (MLLMs) have shown impressive results on various multimodal tasks. However, most existing MLLMs are not well suited for document-oriented tasks, which require fine-grained image perception and information…
Web automation employs intelligent agents to execute high-level tasks by mimicking human interactions with web interfaces. Despite the capabilities of recent Large Language Model (LLM)-based web agents, navigating complex, real-world…
Search engines are a combination of hardware and computer software supplied by a particular company through the website which has been determined. Search engines collect information from the web through bots or web crawlers that crawls the…
The growing prevalence of visually rich documents, such as webpages and scanned/digital-born documents (images, PDFs, etc.), has led to increased interest in automatic document understanding and information extraction across academia and…
World Wide Web consists of more than 50 billion pages online. It is highly dynamic i.e. the web continuously introduces new capabilities and attracts many people. Due to this explosion in size, the effective information retrieval system or…
The importance of recommender systems is growing rapidly due to the exponential increase in the volume of content generated daily. This surge in content presents unique challenges for designing effective recommender systems. Key among these…
Large language models (LLMs) encode a large amount of world knowledge. However, as such knowledge is frozen at the time of model training, the models become static and limited by the training data at that time. In order to further improve…
The advent of large language models (LLMs) brings an opportunity to minimize the effort in search engine result page (SERP) organization. In this paper, we propose GenSERP, a framework that leverages LLMs with vision in a few-shot setting…
This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…
With hundreds of thousands of language models available on Huggingface today, efficiently evaluating and utilizing these models across various downstream, tasks has become increasingly critical. Many existing methods repeatedly learn…
Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation…
The proliferation of online news poses a challenge to extracting structured timelines from unstructured content. While recent studies have shown that Large Language Models (LLMs) can assist Timeline Summarization (TLS), these approaches…
Current AI agents create significant barriers for users by requiring extensive processing to understand web pages, making AI-assisted web interaction slow and expensive. This paper introduces webMCP (Web Machine Context & Procedure), a…
Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In particular, it is unclear whether an MLLM-only…
Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of…
The goal of image cropping is to identify visually appealing crops in an image. Conventional methods are trained on specific datasets and fail to adapt to new requirements. Recent breakthroughs in large vision-language models (VLMs) enable…
Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and…
Multimodal Recommender Systems aim to improve recommendation accuracy by integrating heterogeneous content, such as images and textual metadata. While effective, it remains unclear whether their gains stem from true multimodal understanding…
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical…
Many static benchmarks are beginning to saturate: as models rapidly improve, they achieve near-perfect scores on fixed test sets, leaving little headroom to expose genuine model weaknesses -- and even expert-curated challenge sets quickly…