49 citations · 114 across the 20 of their papers we have counts for
21 papers
Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in Product QA Agents
Ashley Lewis, Michael White, Jing Liu +3
The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination (generating false information) and the high cost of proprietary models. To addres…
Smoothed Embeddings for Robust Language Models
Ryo Hase, Md Rafi Ur Rashid, Ashley Lewis +4
Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful con…
Exploring User-level Gradient Inversion with a Diffusion Prior
Zhuohang Li, Andrew Lowy, Jing Liu +4
We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private in…
Analyzing Inference Privacy Risks Through Gradients in Machine Learning
Zhuohang Li, Andrew Lowy, Jing Liu +4
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privac…
Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
Ryo Hase, Ye Wang, Toshiaki Koike-Akino +2
Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural…
Efficient Differentially Private Fine-Tuning of Diffusion Models
Jing Liu, Andrew Lowy, Toshiaki Koike-Akino +2
The recent developments of Diffusion Models (DMs) enable generation of astonishingly high-quality synthetic samples. Recent work showed that the synthetic samples generated by the…
AutoHLS: Learning to Accelerate Design Space Exploration for HLS Designs
Md Rubel Ahmed, Toshiaki Koike-Akino, Kieran Parsons +1
High-level synthesis (HLS) is a design flow that leverages modern language features and flexibility, such as complex data structures, inheritance, templates, etc., to prototype har…
Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
Andrew Lowy, Zhuohang Li, Jing Liu +3
For small privacy parameter , -differential privacy (DP) provides a strong worst-case guarantee that no membership inference attack (MIA) can succeed at determining whether a…
Stabilizing Subject Transfer in EEG Classification with Divergence Estimation
Niklas Smedemark-Margulies, Ye Wang, Toshiaki Koike-Akino +4
Classification models for electroencephalogram (EEG) data show a large decrease in performance when evaluated on unseen test sub jects. We reduce this performance decrease using ne…
Learning to Learn Quantum Turbo Detection
Bryan Liu, Toshiaki Koike-Akino, Ye Wang +1
This paper investigates a turbo receiver employing a variational quantum circuit (VQC). The VQC is configured with an ansatz of the quantum approximate optimization algorithm (QAOA…
Variational Quantum Compressed Sensing for Joint User and Channel State Acquisition in Grant-Free Device Access Systems
Bryan Liu, Toshiaki Koike-Akino, Ye Wang +1
This paper introduces a new quantum computing framework integrated with a two-step compressed sensing technique, applied to a joint channel estimation and user identification probl…
Line-field Coherent Sensing with LED Illumination
Celalettin Yurdakul, David S. Millar, Hassan Mansour +5
We describe a method of low-coherence interferometry based optical profilometry using standard light-emitting diode (LED) illumination and complementary metal-oxide-semiconductor (…
DNN-assisted optical geometric constellation shaped PSK modulation for PAM4-to-QPSK format conversion gateway node
Takahiro Kodama, Toshiaki Koike-Akino, David S. Millar +2
An optical gateway to convert four-level pulse amplitude modulation to quadrature phase shift keying modulation format having shaping gain was proposed for flexible intensity to ph…
Huffman-Coded Sphere Shaping for Extended-Reach Single-Span Links
Pavel Skvortcov, Ian Phillips, Wladek Forysiak +4
Huffman-coded sphere shaping (HCSS) is an algorithm for finite-length probabilistic constellation shaping, which provides nearly optimal energy efficiency at low implementation com…
Huffman-coded Sphere Shaping and Distribution Matching Algorithms via Lookup Tables
Tobias Fehenberger, David S. Millar, Toshiaki Koike-Akino +3
In this paper, we study amplitude shaping schemes for the probabilistic amplitude shaping (PAS) framework as well as algorithms for constant-composition distribution matching (CCDM…
Analysis of Nonlinear Fiber Interactions for Finite-Length Constant-Composition Sequences
Tobias Fehenberger, David S. Millar, Toshiaki Koike-Akino +3
In order to realize probabilistically shaped signaling within the probabilistic amplitude shaping (PAS) framework, a shaping device outputs sequences that follow a certain nonunifo…
Generative Deep Learning Model for a Multi-level Nano-Optic Broadband Power Splitter
Yingheng Tang, Keisuke Kojima, Toshiaki Koike-Akino +6
We propose a novel Conditional Variational Autoencoder (CVAE) model, enhanced with adversarial censoring and active learning, for the generation of 550 nm broad bandwidth (1250 nm…
Neural Turbo Equalization: Deep Learning for Fiber-Optic Nonlinearity Compensation
Toshiaki Koike-Akino, Ye Wang, David S. Millar +2
Recently, data-driven approaches motivated by modern deep learning have been applied to optical communications in place of traditional model-based counterparts. The application of…
Parallel-Amplitude Architecture and Subset Ranking for Fast Distribution Matching
Tobias Fehenberger, David S. Millar, Toshiaki Koike-Akino +2
A distribution matcher (DM) maps a binary input sequence into a block of nonuniformly distributed symbols. To facilitate the implementation of shaped signaling, fast DM solutions w…
Deep Neural Network Inverse Design of Integrated Nanophotonic Devices
Mohammad H. Tahersima, Keisuke Kojima, Toshiaki Koike-Akino +4
Predicting physical response of an artificially structured material is of particular interest for scientific and engineering applications. Here we use deep learning to predict opti…
Multiset-Partition Distribution Matching
Tobias Fehenberger, David S. Millar, Toshiaki Koike-Akino +2
Distribution matching is a fixed-length invertible mapping from a uniformly distributed bit sequence to shaped amplitudes and plays an important role in the probabilistic amplitude…