Related papers: PRISM: Protocol Refinement through Intelligent Sim…
Large model training beyond tens of thousands of GPUs is an uncharted territory. At such scales, disruptions to the training process are not a matter of if, but a matter of when -- a stochastic process degrading training productivity.…
Surgical image segmentation is essential for robot-assisted surgery and intraoperative guidance. However, existing methods are constrained to predefined categories, produce one-shot predictions without adaptive refinement, and lack…
Recently, researchers have been working toward the development of practical general-purpose protocols for verifiable computation. These protocols enable a computationally weak verifier to offload computations to a powerful but untrusted…
Formal verification is at the heart of model validation and correctness. With model checking, invaluable realizations have been accomplished in software engineering and particularly in software development. By means of this approach,…
We introduce ppsim, a software package for efficiently simulating population protocols, a widely-studied subclass of chemical reaction networks (CRNs) in which all reactions have two reactants and two products. Each step in the dynamics…
Laminate mechanisms are a reliable concept in producing lowcost robots for educational and commercial purposes. These mechanisms are produced using low-cost manufacturing techniques which have improved significantly during recent years and…
Motivated by the substantial achievements observed in Large Language Models (LLMs) in the field of natural language processing, recent research has commenced investigations into the application of LLMs for complex, long-horizon sequential…
The advent of Large Language Models (LLMs) has significantly transformed tasks across Software Engineering. In the context of Business Process Management, LLMs are now being explored as tools to derive process models directly from textual…
NIMS-OS (NIMS Orchestration System) is a Python library created to realize a closed loop of robotic experiments and artificial intelligence (AI) without human intervention for automated materials exploration. It uses various combinations of…
Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajectory-level success…
This paper introduces PRIMETIME, a synthetic generator that supports both benchmarking and fine-tuning of two primitive operations underlying temporal reasoning in Large Language Models (LLMs): parsing and arithmetic on datetimes. Existing…
Network protocol testing is fundamental for modern network infrastructure. However, traditional network protocol testing methods are labor-intensive and error-prone, requiring manual interpretation of specifications, test case design, and…
Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…
The advent of Large Language Models (LLMs) has created new opportunities for the automation of scientific research spanning both experimental processes and computational simulations. This study explores the feasibility of constructing an…
Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…
Rapid progress in imitation learning, foundation models, and large-scale datasets has led to robot manipulation policies that generalize to a wide-range of tasks and environments. However, rigorous evaluation of these policies remains a…
Wireless networks are a common place nowadays and almost all of the modern devices support wireless communication in some form. These networks differ from more traditional computing systems due to the ad-hoc and spontaneous nature of…
Process-supervised reward models (PRMs) excel at providing step-by-step verification for large language model (LLM) outputs in domains like mathematics and coding. However, their application to fields lacking ground-truth answers, such as…
Simulation models often have parameters as input and return outputs to understand the behavior of complex systems. Calibration is the process of estimating the values of the parameters in a simulation model in light of observed data from…
We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows. Our primary goal is to create a minimally interfering…