Related papers: Synapse: Synthetic Application Profiler and Emulat…

This paper addresses the problem of preference learning, which aims to align robot behaviors through learning user specific preferences (e.g. "good pull-over location") from visual demonstrations. Despite its similarity to learning factual…

We propose a perception imitation method to simulate results of a certain perception model, and discuss a new heuristic route of autonomous driving simulator without data synthesis. The motivation is that original sensor data is not always…

This paper introduces Project Synapse, a novel agentic framework designed for the autonomous resolution of last-mile delivery disruptions. Synapse employs a hierarchical multi-agent architecture in which a central Resolution Supervisor…

Collaborative learning among LLM-based agents under federated learning faces challenges, including communication costs, heterogeneity in data, and tool-usage, limiting their effectiveness. We introduce Synapse, a framework that trains a…

Program synthesis techniques construct or infer programs from user-provided specifications, such as input-output examples. Yet most specifications, especially those given by end-users, leave the synthesis problem radically ill-posed,…

Task-based execution frameworks, such as parallel programming libraries, computational workflow systems, and function-as-a-service platforms, enable the composition of distinct tasks into a single, unified application designed to achieve a…

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues…

Today, tool-calling agents are commonly evaluated or tested on static datasets of execution traces, including input commands, agent responses, and associated tool calls. However, internal production datasets are often insufficient or…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data…

The current landscape of scientific research is widely based on modeling and simulation, typically with complexity in the simulation's flow of execution and parameterization properties. Execution flows are not necessarily straightforward…

As smartphones are widely adopted, mobile applications (apps) are emerging to provide critical services such as food delivery and telemedicine. While bring convenience to everyday life, this trend may create barriers for older adults who…

The rapid advancement of AI and computer vision has significantly increased the demand for high-quality annotated datasets, particularly for semantic segmentation. However, creating such datasets is resource-intensive, requiring substantial…

We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task performance using only limited unannotated real data. This addresses a critical and open…

Workflows are critical for scientific discovery. However, the sophistication, heterogeneity, and scale of workflows make building, testing, and optimizing them increasingly challenging. Furthermore, their complexity and heterogeneity make…

Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-consuming and expensive annotations. However, previous…

The present work aims to enhance the application logs of an hypothetical infrastructure platform, and to build an App that displays the synthetic data about performance, anomalies and security incidents synthesized in the form of a…

In formal synthesis of reactive systems an implementation of a system is automatically constructed from its formal specification. The great advantage of synthesis is that the resulting implementation is correct by construction; therefore…

Synthetic data and simulators have the potential to markedly improve the performance and robustness of recommendation systems. These approaches have already had a beneficial impact in other machine-learning driven fields. We identify and…

Profiling techniques are used extensively at different parts of the computing stack to achieve many goals. One major goal is to make a piece of software execute more efficiently on a specific hardware platform, where efficiency spans…