Search Results for author:
Found 15 papers, 4 papers with code
Improving Parallel Program Performance Through DSL-Driven Code Generation with LLM Optimizers
To maximize the application performance, we use an LLM optimizer to improve an agentic system that generates the mapper code.
Putting People in Their Place: Affordance-Aware Human Insertion into Scenes
Given a scene image with a marked region and an image of a person, we insert the person into the scene while respecting the scene affordances.
Training with Mixed-Precision Floating-Point Assignments
Hence, it is important to use a precision assignment -- a mapping from all tensors (arising in training) to precision levels (high or low) -- that keeps most of the tensors in low precision and leads to sufficiently accurate models.
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
For a neural network with bias parameters, we first prove that the incorrect set is always empty.
Programmatic Concept Learning for Human Motion Description and Synthesis
We introduce Programmatic Motion Concepts, a hierarchical motion representation for human actions that captures both low-level motion and high-level description as motion concepts.
Optimizing Mixture of Experts using Dynamic Recompilations
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs).
Hierarchical Motion Understanding via Motion Programs
We posit that adding higher-level motion primitives, which can capture natural coarser units of motion such as backswing or follow-through, can be used to improve downstream analysis tasks.
Task Bench: A Parameterized Benchmark for Evaluating Parallel Runtime Performance
We present Task Bench, a parameterized benchmark designed to explore the performance of parallel and distributed programming systems under a variety of application scenarios.
Distributed, Parallel, and Cluster Computing
SPoC: Search-based Pseudocode to Code
Given test cases as a mechanism to validate programs, we search over the space of possible translations of the pseudocode to find a program that passes the validation.
Ranked #2 on
Program Synthesis
on SPoC TestP
Redundancy-Free Computation Graphs for Graph Neural Networks
Graph Neural Networks (GNNs) are based on repeated aggregations of information across nodes' neighbors in a graph.
Beyond Data and Model Parallelism for Deep Neural Networks
We also propose FlexFlow, a deep learning framework that uses guided randomized search of the SOAP space to find a fast parallelization strategy for a specific parallel machine.
Distributed, Parallel, and Cluster Computing
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks
The past few years have witnessed growth in the computational requirements for training deep convolutional neural networks.
Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks
The past few years have witnessed growth in the computational requirements for training deep convolutional neural networks.
Exploring the Hidden Dimension in Accelerating Convolutional Neural Networks
DeePa is a deep learning framework that explores parallelism in all parallelizable dimensions to accelerate the training process of convolutional neural networks.
Synthesizing Program Input Grammars
We present an algorithm for synthesizing a context-free grammar encoding the language of valid program inputs from a set of input examples and blackbox access to the program.
Programming Languages
