8 papers
Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning
Yiwei Chen, Lichi Li, Kai Cheung +2
We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We adopt a data-centric approach…
kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation
Rohan Siva, Kai Cheung, Lichi Li +1
Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelin…
A Latent Space Framework for Modeling Transient Engine Emissions Using Joint Embedding Predictive Architectures
Ganesh Sundaram, Tobias Gehra, Jonas Ulmen +3
Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing…
Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation
Ganesh Sundaram, Jonas Ulmen, Daniel Görges
The transition from monolithic to multi-component neural architectures in advanced neural network controllers poses substantial challenges due to the high computational complexity…
Application-Specific Component-Aware Structured Pruning of Deep Neural Networks in Control via Soft Coefficient Optimization
Ganesh Sundaram, Jonas Ulmen, Amjad Haider +1
Deep neural networks (DNNs) offer significant flexibility and robust performance. This makes them ideal for building not only system models but also advanced neural network control…
Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures
Jonas Ulmen, Ganesh Sundaram, Daniel Görges
With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for…