Computer Science
Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RTP-LLM, a high-performance inference engine for industrial-scale LLM deployment, successfully…
AI is transforming life sciences research at unprecedented speed, accelerating discovery across protein structure prediction, genome modeling, and drug development (Jumper et al., 2021; Mak et al., 2024). Yet this rapid advancement, coupled…
The substance of this paper is the description of the use of Retrieval-Augmented Generation (RAG) for specific digital collections of cultural assets. The collections are provided by institutions operating in the cultural sector. The…
Users of search-augmented LLMs rely on citations as evidence that responses are grounded in real sources, and rarely verify the cited pages themselves. Millions of queries per day now pass through these systems, making citation quality a…
Large language models (LLMs) are increasingly used to generate scientific reports, but they can produce references that appear plausible while containing corrupted metadata or pointing to papers that do not exist. We introduce CiteCheck, a…
A real-time multicore system requires delay bounds on access to shared resources. These resources include the kernel, which has potentially many non-preemptible critical sections guarded by one or more different synchronization primitives.…
Linux is the foundation of the digital age, accounting for the majority of the cloud and mobile OS markets. Any device that runs Linux uses the Linux page cache, a central pillar in OS and application performance, serving to reduce…
KV cache management is essential for efficient LLM inference. To maximize utilization, existing inference engines evict finished requests' KV cache if new requests are waiting. This policy breaks for agentic workloads, which interleave LLM…
Scientific papers make claims about prior work backed by citations. Verifying those citations at scale (that each cited paper exists, says what the citation claims, and is itself reliable) is structurally beyond what human review can…
We present BookReconciler, an open-source tool for enhancing and clustering book data. BookReconciler allows users to take spreadsheets with minimal metadata, such as book title and author, and automatically 1) add authoritative, persistent…
Authorship attribution asks whether two pieces of text share a writer, but topical confound makes the task deceptively easy: two authors covering the same topic may look more alike than one author covering two topics. Scholarly prose offers…
This study employs scientometric methods to assess the research output and performance of the University of Nigeria from 2014 to 2023. By analyzing publication trends, citation patterns, and collaboration networks, the research aims to…
Sustaining open data infrastructures over time is a complex puzzle, involving dynamic funding models and relationships with customers, collaborators, and competitors. Despite their importance, these mechanisms are often hidden from view,…
LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g.,…
The web is often treated as a durable record of institutional and social life, yet in practice it is fragile, revisable, and frequently ephemeral. Domains change, redesigns erase earlier material, institutions relocate, maintainers…
This article examines the case of two papers published in Naturwissenschaften by the physicist Max Planck that were retrospectively marked as retracted on Springer digital platform. Rather than originating in scientific fraud, these…
Secure containers isolate each container with its own kernel, mitigating shared-kernel attacks prevalent in traditional container systems. However, existing designs still face a fundamental isolation--performance trade-off. Nested-cloud…
Object-level management of tiered memory has been studied to address the inefficiencies in page-based systems. However, object-level management for CXL-tiered memory remains underexplored due to CXL's tight performance budget and load/store…
Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across multiple verifier queries, while the latter reduces each…
The academic journal zoning system is central to evaluating research talent, funding, and institutions. The CAS journal partition system, one of East Asia's most widely used tools, will cease operation in March 2026, creating a policy gap.…