8 papers
Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling
Zhimin Li, Harshitha Menon, Charles Jekel +2
Neural networks are used as generative surrogate models for scientific discovery, which are trainable approximations of scientific simulations. These models enable users to replace…
End-to-End Context Compression at Scale
Ang Li, Sean McLeish, Haozhe Chen +12
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degra…
Learning Reasoning World Models for Parallel Code
Gautam Singh, Arjun Guha, Bhavya Kailkhura +1
Large language models have shown remarkable ability in serial code generation, but they still struggle with parallel code for which training data is comparatively scarce. A common…
Steering Code LLMs with Activation Directions for Language and Library Control
Md Mahbubur Rahman, Arjun Guha, Harshitha Menon
Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear direct…
Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems
Harshitha Menon, Charles F. Jekel, Kevin Korner +15
Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design spaces. In order to enable high-i…
Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
Meir H. Shachar, Dane M. Sterbentz, Harshitha Menon +10
Inertial fusion energy promises nearly unlimited, clean power if it can be achieved. However, the design and engineering of fusion systems requires controlling and manipulating mat…