24 citations · 76 across the 18 of their papers we have counts for
22 papers
Flux Vacua, Asymptotic Periods, and Relatively Anosov Representations
Paul Balavoine, Severin Lüst
We develop a topological method to detect classical flux vacua of M-theory on Calabi-Yau fourfolds with a single complex structure modulus using only asymptotic period data and mon…
LocalTrain: Integer-Only Local Learning for Energy-Efficient CNN Training on Edge FPGAs
Shiqi Ding, Xuanyu Liang, Xinyang Liu +4
Local learning reduces cross-layer training dependencies, but an efficient accelerator must still retain operands, accumulate gradients, and select quantization scales. We present…
Alkaid: A Compiler Framework for Ultra-Low-Latency Kernels on Hardware
Chang Sun, Zhiqiang Que, Dimitrios Danopoulos +3
Ultra-low-latency machine learning and data processing pipelines operating on the sub-microsecond level often contain static dataflow kernels that require fine-grained bitwidth con…
HeteroReason: Heterogeneous FPGA-GPU Acceleration for Disaggregated Speculative Reasoning
Zehuan Zhang, Quan Deng, Zibo Ren +8
Large Reasoning Models (LRMs) have achieved state-of-the-art performance in reasoning tasks by utilizing Chain-of-Thought (CoT) reasoning. To achieve fast execution speed, speculat…
FQTree: Fine-grained Quantization and Hardware Generation of Boosted Decision Trees
Zhiqiang Que, Chang Sun, Haiyang Wang +6
Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging. Existing designs often rely on uniform or man…
SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving
Hongyuan Liu, Yawei Li, Zhiqiang Que +3
Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-…
FFR: Forward-Forward Learning for Regression
Xinyang Liu, Xuanyu Liang, Shiqi Ding +4
The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neural networks through purely loca…
HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference
Chang Sun, Zhiqiang Que, Bakhtiar Zadeh +4
Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitive…
Low-Latency FPGA Control System for Real-Time Neural Network Processing in CCD-Based Trapped-Ion Qubit Measurement
Binglei Lou, Gautham Duddi Krishnaswaroop, Filip Wojcicki +5
Accurate and low-latency qubit state measurement is critical for trapped-ion quantum computing. While deep neural networks (DNNs) have been integrated to enhance detection fidelity…
JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers
Ruoqing Zheng, Chang Sun, Qibin Liu +7
We present JetFormer, a versatile and scalable encoder-only Transformer architecture for particle jet tagging at the Large Hadron Collider (LHC). Unlike prior approaches that are o…
Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges
Guanxi Lu, Hao Mark Chen, Zhiqiang Que +2
Large language models (LLMs) have shown promising performance across various tasks. However, their autoregressive decoding process poses significant challenges for efficient deploy…
Sub-microsecond Transformers for Jet Tagging on FPGAs
Lauri Laatu, Chang Sun, Arianna Cox +7
We present the first sub-microsecond transformer implementation on an FPGA achieving competitive performance for state-of-the-art high-energy physics benchmarks. Transformers have…
da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs
Chang Sun, Zhiqiang Que, Vladimir Loncar +2
Neural networks with a latency requirement on the order of microseconds, like the ones used at the CERN Large Hadron Collider, are typically deployed on FPGAs fully unrolled and pi…
MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration
Zhiqiang Que, Jose G. F. Coutinho, Ce Guo +2
This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, suc…
HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Chang Sun, Zhiqiang Que, Thea K. Årrestad +4
Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quanti…
Ultrafast jet classification on FPGAs for the HL-LHC
Patrick Odagiu, Zhiqiang Que, Javier Duarte +13
Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, w…
When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA
Hongxiang Fan, Hao Chen, Liam Castelli +4
Bayesian Neural Networks (BayesNNs) have demonstrated their capability of providing calibrated prediction for safety-critical applications such as medical imaging and autonomous dr…
MetaML: Automating Customizable Cross-Stage Design-Flow for Deep Learning Acceleration
Zhiqiang Que, Shuo Liu, Markus Rognlien +3
This paper introduces a novel optimization framework for deep neural network (DNN) hardware accelerators, enabling the rapid development of customized and automated design flows. M…
LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics
Zhiqiang Que, Hongxiang Fan, Marcus Loo +5
This work presents a novel reconfigurable architecture for Low Latency Graph Neural Network (LL-GNN) designs for particle detectors, delivering unprecedented low latency performanc…
Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator
Hongxiang Fan, Martin Ferianc, Zhiqiang Que +4
Recent advances in algorithm-hardware co-design for deep neural networks (DNNs) have demonstrated their potential in automatically designing neural architectures and hardware desig…
Accelerating Recurrent Neural Networks for Gravitational Wave Experiments
Zhiqiang Que, Erwei Wang, Umar Marikar +10
This paper presents novel reconfigurable architectures for reducing the latency of recurrent neural networks (RNNs) that are used for detecting gravitational waves. Gravitational i…
Optimizing Bayesian Recurrent Neural Networks on an FPGA-based Accelerator
Martin Ferianc, Zhiqiang Que, Hongxiang Fan +2
Neural networks have demonstrated their outstanding performance in a wide range of tasks. Specifically recurrent architectures based on long-short term memory (LSTM) cells have man…