Publications
Type
Area
Institution
Lead Author
HIDA: A Hierarchical Dataflow Compiler for High-Level Synthesis
hls4ml: low latency neural network inference on FPGAs
Graph Neural Network-based Track finding as a Service with ACTS
NSF HDR ML Anomaly Detection Challenge
A search for binary mergers in archival LIGO data using aframe, a machine learning detection pipeline
A machine-learning pipeline for real-time detection of gravitational waves from compact binary coalescences
Energy Frontier Exploration using Particle Physics and AI
A machine-learning pipeline for real-time detection of gravitational waves from compact binary coalescences
Point Transformer V3: Simpler, Faster, Stronger
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
MIT
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Uncertainty Quantification and Anomaly Detection with Evidential Deep Learning
Ultra Fast Transformers on FPGAs for Particle Physics Experiments
University of Washington | MIT
Ultra Fast Transformers on FPGAs for Particle Physics Experiments
University of Washington | MIT
The Stability of Positional Encodings for Graphs
Supernova Neutrino Burst Detection with Mineral Detectors
On the Stability of Expressive Positional Encodings for Graphs
Neuroscience ML challenges using CodaBench: Decoding multi-limb trajectories from two-photon calcium imaging
High Pileup Particle Tracking with Object Condensation
FPGA Deployment of LFADS for Real-time Neuroscience Experiments
University of Washington
Explainable AI for Interpretability of Neural Networks
Evaluating the Quality of HLS4ML’s Basic Neural Network Implementations on FPGAs
Deep Learning Applications for Particle Physics in Tracking and Calorimetry
The ZTF Source Classification Project: III. A Catalog of Variable Sources
Quantifying the Efficiency of High-Level Synthesis for Machine Learning Inference
University of Washington
Low Latency Edge Classification GNN for Particle Trajectory Tracking on FPGAs
University of Washington | University of San Diego
HIDA: A Hierarchical Dataflow Compiler for High-Level Synthesis
Machine Learning Acceleration — Quantization Process and Tools Development
Machine Learning acceleration in the Global Event Processor of the ATLAS Trigger Update
By Zhixing Jiang | University of Washington
Accelerating CNNs on FPGAs for Particle Energy Reconstruction
Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml
University of Washington | MIT
Portable Acceleration of CMS Mini-AOD Production with Coprocessors as a Service
By William Patrick Mccormack | MIT
Jets as sets or graphs: Fast jet classification on FPGAs for efficient triggering at the HL-LHC
MLPF: Machine Learning for Particle Flow
Scalable neural network models and terascale datasets for particle-flow reconstruction
By Joosep Pata
Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
ACTS as a Service
FKeras: A Sensitivity Analysis Tool for Edge Neural Networks
University of California San Diego
ScaleHLS, a Scalable High-level Synthesis Framework with Multi-level Transformations and Optimizations
AutoScaleDSE: A Scalable Design Space Exploration Engine for High-Level Synthesis
Track reconstruction for the ATLAS Phase-II High-Level Trigger using Graph Neural Networks on FPGAs
By Santosh Parajuli | University of Illinois at Urbana-Champaign
FPGA Deployment of LFADS for Real-time Neuroscience Experiments
University of Washington
Quantifying the Efficiency of High-Level Synthesis for Machine Learning Inference
University of Washington
Fast ML in the NSF HDR Institute: A3D3
Community Vision, Needs, and Progress
ZTF SCoPe: A Catalog of Variable Sources
GWAK: Gravitational-Wave Anomalous Knowledge with Recurrent Autoencoders
University of Minnesota | MIT
Parameter estimation using Likelihood-free Inference
By Malina Desai | University of Minnesota | MIT
BEVFusion-R: Efficient and Deployment-Ready Camera-Radar Fusion
MIT
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
MIT
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
MIT
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation
MIT
SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
Purdue University | Georgia Institute of Technology
Structural Re-weighting Improves Graph Domain Adaptation
Progress towards an improved particle flow algorithm at CMS with machine learning, 2023, ACAT
Semi-supervised Graph Neural Networks for Pileup Noise Removal, 2022, NeurIPS AI4Science, EPJC
Interpretable Geometric Deep Learning via Learnable Randomness Injection, 2023, ICLR
Neighborhood-aware Scalable Temporal Network Representation Learning, 2022, LoG
Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning, 2022, VLDB
TorchSparse++: Efficient Point Cloud Engine
NMMA: A nuclear-physics and multi-messenger astrophysics framework to analyze binary neutron star mergers, 2023, submitted
Tutorials on ScaleHSL, FPGA, Feb. 27, 2022
Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism, 2022, ICML
Javier Duarte, Artificial Intelligence at the Edge of Particle Physics, HEP Seminar, Columbia University, November 17, 2021
Applications and Techniques for Fast Machine Learning in Science, 2021, Submitted to Front. Big Data
PointAcc: Efficient Point Cloud Accelerator, 2021, MICRO
Shih-Chieh Hsu, NSF HDR Institute: Accelerated Artificial Intelligence Algorithms for Data-Driven Discovery (A3D3), Fast ML General Meeting, October 1, 2021
ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation, 2022, HPCA
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution, 2020, ECCV