Related papers: Multiparty Session Typing, Embedded (Technical Rep…
In the modern era of multi-core systems, the main aim is to utilize the cores properly. This utilization can be done by concurrent programming. But developing a flawless and well-organized concurrent program is difficult. Software…
Secure multi-party computation (MPC) allows a set of parties to compute a function jointly while keeping their inputs private. Compared with the MPC based on garbled circuits,some recent research results show that MPC based on secret…
Multimodal transformers integrate diverse data types like images, audio, and text, advancing tasks such as audio-visual understanding and image-text retrieval; yet their high parameterization limits deployment on resource-constrained edge…
In order to perform machine learning among multiple parties while protecting the privacy of raw data, privacy-preserving machine learning based on secure multi-party computation (MPL for short) has been a hot spot in recent. The…
This paper introduces NEST (Network-Enforced Session Types), a runtime verification framework that moves application-level protocol monitoring into the network fabric. Unlike prior work that instruments or wraps application code, we…
Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: it facilitates training of machine-learning models…
Prompting has recently been shown as a promising approach for applying pre-trained language models to perform downstream tasks. We present Multi-Stage Prompting (MSP), a simple and automatic approach for leveraging pre-trained language…
The Message Passing Interface (MPI) is the de facto standard message-passing infrastructure for developing parallel applications. Two decades after the first version of the library specification, MPI-based applications are nowadays…
Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it…
This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…
Secure multiparty computation (MPC) techniques enable multiple parties to compute joint functions over their private data without sharing that data with other parties, typically by employing powerful cryptographic protocols to protect…
Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…
In designing distributed and parallel systems there are several approaches for programming interactions in a multiprocess environment. Usually, these approaches take care only of synchronization or communication in two-party interactions.…
Secure Multi-Party Computation (MPC) allows mutually distrusting parties to run joint computations without revealing private data. Current MPC algorithms scale poorly with data size, which makes MPC on "big data" prohibitively slow and…
Session types, types for structuring communication between endpoints in distributed systems, are recently being integrated into mainstream programming languages. In practice, a very important notion for dealing with such types is that of…
Secure Multi-Party Computation (SMPC) allows a set of parties to securely compute a functionality in a distributed fashion without the need for any trusted external party. Usually, it is assumed that the parties know each other and have…
Embedded systems represent a billionaire market and are present in most of the processors produced in the world.Embedded software interacts with external peripherals such as sensors and actuators through drivers. The strong interaction…
Recent advancements in large language models (LLMs) integrating explicit reasoning, such as OpenAI's o3-mini, DeepSeek-R1, and QWQ-32B, enable smaller models to solve complex tasks by generating intermediate reasoning steps prior to…
Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity…
Session types provide a principled approach to typed communication protocols that guarantee type safety and protocol fidelity. Formalizations of session-typed communication are typically based on process calculi, concurrent lambda calculi,…