7 papers
MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts
Abhinav Jain, Xinyu Yao, Thomas Reps +1
Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using doma…
DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs
Xinyu Yao, Daniel Bourgeois, Abhinav Jain +5
We study the problem of assigning operations in a dataflow graph to devices to minimize execution time in a work-conserving system, with emphasis on complex machine learning worklo…
Cost-Aware Optimization for Agentic Query Execution
Lunyiu Nie, Yilin Xia, Yiren Liu +2
Classical query optimization searches over algebraically equivalent plans that differ only in cost. This assumption breaks once LLM-backed operators enter the picture: their placem…
Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor Computation
Yuxin Tang, Zhiyuan Xin, Zhimin Ding +4
A \emph{tensor-relational} computation is a relational computation where individual tuples carry vectors, matrices, or higher-dimensional arrays. An advantage of tensor-relational…
Auditing Information Disclosure During LLM-Scale Gradient Descent Using Gradient Uniqueness
Sleem Abdelghafar, Maryam Aliakbarpour, Chris Jermaine
Disclosing information via the publication of a machine learning model poses significant privacy risks. However, auditing this disclosure across every datapoint during the training…
Resource-efficient Inference with Foundation Model Programs
Lunyiu Nie, Zhimin Ding, Kevin Yu +3
The inference-time resource costs of large language and vision models present a growing challenge in production deployments. We propose the use of foundation model programs, i.e.,…