Showing 1–20 of 20 results
/ Date/ Name
Mar 16, 2026Multi-Mode Pneumatic Artificial Muscles Driven by Hybrid Positive-Negative PressureOct 30, 2025ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning SystemsSep 22, 2025Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE ServingMar 10, 2025WHERE-Bot: a Wheel-less Helical-ring Everting Robot Capable of Omnidirectional LocomotionDec 26, 2024How Panel Layouts Define Manga: Insights from Visual Ablation ExperimentsFeb 15, 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild RobotsNov 1, 2023Relax: Composable Abstractions for End-to-End Dynamic Machine LearningMay 19, 2023Language-universal phonetic encoder for low-resource speech recognitionMay 19, 2023Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech RecognitionMar 22, 2023A multi-functional simulation platform for on-demand ride service operationsJul 9, 2022TensorIR: An Abstraction for Automatic Tensorized Program OptimizationApr 2, 2021Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature RepresentationMar 28, 2021Quantifying Bias in Automatic Speech RecognitionDec 17, 2020The effectiveness of unsupervised subword modeling with autoregressive and cross-lingual phone-aware networksNov 3, 2020Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck FeaturesJul 29, 2020Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource LanguagesJul 25, 2020Unsupervised Subword Modeling Using Autoregressive Pretraining and Cross-Lingual Phone-Aware ModelingAug 9, 2019Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword ModelingJun 17, 2019Improving Unsupervised Subword Modeling via Disentangled Speech Representation Learning and TransformationJun 17, 2019Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling