Related papers: Knowledge is Overrated: A zero-knowledge machine l…

The increasing data rates and complexity of detectors at the Large Hadron Collider (LHC) necessitate fast and efficient machine learning models, particularly for rapid selection of what data to store, known as triggering. Building on recent…

To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have…

As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for…

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Collision-resistant, cryptographic hash (CRH) functions have long been an integral part of providing security and privacy in modern systems. Certain constructions of zero-knowledge proof (ZKP) protocols aim to utilize CRH functions to…

Machine Learning as a service (MLaaS) permits resource-limited clients to access powerful data analytics services ubiquitously. Despite its merits, MLaaS poses significant concerns regarding the integrity of delegated computation and the…

Large language model (LLM) routers improve the efficiency of multi-model systems by directing each query to the most appropriate model while leveraging the diverse strengths of heterogeneous LLMs. Most existing approaches frame routing as a…

The rapid adoption of Large Language Models (LLMs) has driven a growing demand for efficient inference, particularly in latency-sensitive applications such as chatbots and personalized assistants. Unlike traditional deep neural networks,…

Schema matching (SM) and entity matching (EM) tasks are crucial for data integration. While large language models (LLMs) have shown promising results in these tasks, they suffer from hallucinations and confusion about task instructions.…

Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous works makes LLM-based planning error-prone and fragile. On the…

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from…

Device-edge co-inference, which partitions a deep neural network between a resource-constrained mobile device and an edge server, recently emerges as a promising paradigm to support intelligent mobile applications. To accelerate the…

Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, security, and update validation. We propose ZK-HybridFL, a secure…

Indistinguishability is a fundamental principle of cryptographic security, crucial for securing data transmitted between Internet of Things (IoT) devices. This principle ensures that an attacker cannot distinguish between the encrypted…

Quantum Machine Learning (QML) is an exciting tool that has received significant recent attention due in part to advances in quantum computing hardware. While there is currently no formal guarantee that QML is superior to classical ML for…

At the Large Hadron Collider (LHC), the trigger systems for the detectors must be able to process a very large amount of data in a very limited amount of time, so that the nominal collision rate of 40 MHz can be reduced to a data rate that…

Fine-tuning large language models (LLMs) with high-quality knowledge has been shown to enhance their performance effectively. However, there is a paucity of research on the depth of domain-specific knowledge comprehension by LLMs and the…

Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly understood. Current methods predominantly treat VLMs as…

As large language models (LLMs) continue to grow in size, fewer users are able to host and run models locally. This has led to increased use of third-party hosting services. However, in this setting, there is a lack of guarantees on the…