Related papers: Aggregator Reuse and Extension for Richer Web Arch…
A system that could reliably identify and sum up the most important points of a conversation would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls. Recent…
Modeling of long history data suffers from long-context window attention dilution, system efficiency and catastrophic forgetting problems, where naive linear scaling approach like LastN would fail. We introduce Memento, a personalized…
Archive collections are nowadays mostly available through search engines interfaces, which allow a user to retrieve documents by issuing queries. The study of these collections may be, however, impaired by some aspects of search engines,…
LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To address this issue, we propose MemSearcher, an agent framework…
Archiving the web is socially and culturally critical, but presents problems of scale. The Internet Archive's Wayback Machine can replay captured web pages as they existed at a certain point in time, but it has limited ability to provide…
Working memory involves the temporary retention of information over short periods. It is a critical cognitive function that enables humans to perform various online processing tasks, such as dialing a phone number, recalling misplaced…
Many concurrent algorithms require processes to perform fetch-and-add operations on a single memory location, which can be a hot spot of contention. We present a novel algorithm called Aggregating Funnels that reduces this contention by…
Upon replay, JavaScript on archived web pages can generate recurring HTTP requests that lead to unnecessary traffic to the web archive. In one example, an archived page averaged more than 1000 requests per minute. These requests are not…
Sequence-to-sequence models provide a viable new approach to generative summarization, allowing models that are no longer limited to simply selecting and recombining sentences from the original text. However, these models have three…
We present a framework for web-scale archiving of the dark web. While commonly associated with illicit and illegal activity, the dark web provides a way to privately access web information. This is a valuable and socially beneficial tool to…
Disaggregated memory is an upcoming data center technology that will allow nodes (servers) to share data efficiently. Sharing data creates a debate on the level of cache coherence the system should provide. While current proposals aim to…
Web archive analytics is the exploitation of publicly accessible web pages and their evolution for research purposes -- to the extent organizationally possible for researchers. In order to better understand the complexity of this task, the…
Real-world tasks often lack large labeled datasets, motivating extensive work on learning in low-data regimes. However, existing approaches such as few-shot prompting, instruction tuning, and synthetic data generation, continue to treat…
Web archiving services play an increasingly important role in today's information ecosystem, by ensuring the continuing availability of information, or by deliberately caching content that might get deleted or removed. Among these, the…
Memristors are passive elements that allow us to store information using a single element per bit. However, this is not the only utility of the memristor. Considering the physical chemical structure of the element used, the memristor can…
An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its…
Annotation graphs and annotation servers offer infrastructure to support the analysis of human language resources in the form of time-series data such as text, audio and video. This paper outlines areas of common need among empirical…
In edge computing use cases (e.g., smart cities), where several users and devices may be in close proximity to each other, computational tasks with similar input data for the same services (e.g., image or video annotation) may be offloaded…
When learning a novel complex task, people often form efficient reusable abstractions that simplify future work, despite uncertainty about the future. We study this process in a visual puzzle task where participants define and reuse helpers…
In this paper, we present a meta-analysis of several Web content extraction algorithms, and make recommendations for the future of content extraction on the Web. First, we find that nearly all Web content extractors do not consider a very…