b'Vikas Chandra'

research

∙ 09/19/2023

FoleyGen: Visually-Guided Audio Generation

Recent advancements in audio generation have been spurred by the evoluti...

0 Xinhao Mei, et al. ∙

research

∙ 09/15/2023

Stack-and-Delay: a new codebook pattern for music generation

In language modeling based music generation, a generated waveform is rep...

0 Gaël Le Lan, et al. ∙

research

∙ 09/05/2023

TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models

Automatic Speech Recognition (ASR) models need to be optimized for speci...

0 Yuan Shangguan, et al. ∙

research

∙ 07/01/2023

Revisiting Sample Size Determination in Natural Language Understanding

Knowing exactly how many data points need to be labeled to achieve a cer...

0 Ernie Chang, et al. ∙

research

∙ 06/08/2023

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

Weight-sharing supernet has become a vital component for performance est...

0 Ganesh Jawahar, et al. ∙

research

∙ 05/29/2023

LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Several post-training quantization methods have been applied to large la...

0 Zechun Liu, et al. ∙

research

∙ 12/12/2022

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion

Fusing camera with LiDAR is a promising technique to improve the accurac...

0 Lemeng Wu, et al. ∙

research

∙ 12/07/2022

SDRM3: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads

Emerging real-time multi-model ML (RTMM) workloads such as AR/VR and dro...

0 Seah Kim, et al. ∙

research

∙ 12/04/2022

Fast Point Cloud Generation with Straight Flows

Diffusion models have emerged as a powerful tool for point cloud generat...

0 Lemeng Wu, et al. ∙

research

∙ 11/16/2022

XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse

Real-time multi-model multi-task (MMMT) workloads, a new form of deep le...

0 Hyoukjun Kwon, et al. ∙

research

∙ 11/09/2022

LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting

This paper proposes a hardware-efficient architecture, Linearized Convol...

0 Haichuan Yang, et al. ∙

research

∙ 06/02/2022

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

Efficient deep neural network (DNN) models equipped with compact operato...

10 Yonggan Fu, et al. ∙

research

∙ 03/29/2022

Streaming parallel transducer beam search with fast-slow cascaded encoders

Streaming ASR with strict latency constraints is required in many speech...

0 Jay Mahadeokar, et al. ∙

research

∙ 11/02/2021

Low-Rank+Sparse Tensor Compression for Neural Networks

Low-rank tensor compression has been proposed as a promising approach to...

0 Cole Hawkins, et al. ∙

research

∙ 11/01/2021

HRViT: Multi-Scale High-Resolution Vision Transformer

Vision transformers (ViTs) have attracted much attention for their super...

0 Jiaqi Gu, et al. ∙

research

∙ 10/15/2021

Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet

From wearables to powerful smart devices, modern automatic speech recogn...

0 Haichuan Yang, et al. ∙

research

∙ 07/09/2021

Noisy Training Improves E2E ASR for the Edge

Automatic speech recognition (ASR) has become increasingly ubiquitous on...

0 Dilin Wang, et al. ∙

research

∙ 06/16/2021

Collaborative Training of Acoustic Encoders for Speech Recognition

On-device speech recognition requires training models of different sizes...

0 Varun Nagaraja, et al. ∙

research

∙ 04/26/2021

Improve Vision Transformers Training by Suppressing Over-smoothing

Introducing the transformer structure into computer vision tasks holds t...

4 Chengyue Gong, et al. ∙

research

∙ 03/02/2021

Feature-Align Network and Knowledge Distillation for Efficient Denoising

Deep learning-based RAW image denoising is a quintessential problem in i...

37 Lucas D. Young, et al. ∙

research

∙ 03/02/2021

Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search

Modern day computing increasingly relies on specialization to satiate gr...

0 Kartik Hegde, et al. ∙

research

∙ 02/23/2021

Memory-efficient Speech Recognition on Smart Devices

Recurrent transducer models have emerged as a promising solution for spe...

0 Ganesh Venkatesh, et al. ∙

research

∙ 02/16/2021

AlphaNet: Improved Training of Supernet with Alpha-Divergence

Weight-sharing neural architecture search (NAS) is an effective techniqu...

3 Dilin Wang, et al. ∙

research

∙ 01/25/2021

CPT: Efficient Deep Neural Network Training via Cyclic Precision

Low-precision deep neural network (DNN) training has gained tremendous a...

0 Yonggan Fu, et al. ∙

research

∙ 12/03/2020

EVRNet: Efficient Video Restoration on Edge Devices

Video transmission applications (e.g., conferencing) are gaining momentu...

0 Sachin Mehta, et al. ∙

research

∙ 11/30/2020

ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

Scale variance among different sizes of body parts and objects is a chal...

0 Hsin-Pai Cheng, et al. ∙

research

∙ 11/25/2020

Can Temporal Information Help with Contrastive Self-Supervised Learning?

Leveraging temporal information has been regarded as essential for devel...

10 Yutong Bai, et al. ∙

research

∙ 11/23/2020

KeepAugment: A Simple Information-Preserving Data Augmentation Approach

Data augmentation (DA) is an essential technique for training state-of-t...

22 Chengyue Gong, et al. ∙

research

∙ 11/18/2020

AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

Neural architecture search (NAS) has shown great promise designing state...

0 Dilin Wang, et al. ∙

research

∙ 10/28/2020

DNA: Differentiable Network-Accelerator Co-Search

Powerful yet complex deep neural networks (DNNs) have fueled a booming d...

0 Yongan Zhang, et al. ∙

research

∙ 08/22/2020

One Weight Bitwidth to Rule Them All

Weight quantization for deep ConvNets has shown promising results for ap...

0 Ting-Wu Chin, et al. ∙

research

∙ 07/08/2020

NASGEM: Neural Architecture Search via Graph Embedding Method

Neural Architecture Search (NAS) automates and prospers the design of ne...

0 Hsin-Pai Cheng, et al. ∙

research

∙ 02/13/2020

Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization

Neural network accelerator is a key enabler for the on-device AI inferen...

0 Meng Li, et al. ∙

research

∙ 02/10/2020

Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks

Neural Architecture Search (NAS) has demonstrated its power on various A...

0 Lei Yang, et al. ∙

research

∙ 12/30/2019

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

Personalized recommendation systems leverage deep learning models and ac...

0 Liu Ke, et al. ∙

research

∙ 10/07/2019

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent

Designing energy-efficient networks is of critical importance for enabli...

0 Dilin Wang, et al. ∙

research

∙ 09/13/2019

HERALD: Optimizing Heterogeneous DNN Accelerators for Edge Devices

Recent advances in deep neural networks (DNNs) have made DNNs the backbo...

0 Hyoukjun Kwon, et al. ∙

research

∙ 06/02/2018

Federated Learning with Non-IID Data

Federated learning enables resource-constrained edge compute devices, su...

0 Yue Zhao, et al. ∙

research

∙ 01/19/2018

CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs

Deep Neural Networks are becoming increasingly popular in always-on IoT ...

0 Liangzhen Lai, et al. ∙

research

∙ 01/12/2018

Not All Ops Are Created Equal!

Efficient and compact neural network models are essential for enabling t...

0 Liangzhen Lai, et al. ∙

research

∙ 12/05/2017

Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks

Hardware acceleration of Deep Neural Networks (DNNs) aims to tame their ...

0 Hardik Sharma, et al. ∙

research

∙ 11/20/2017

Hello Edge: Keyword Spotting on Microcontrollers

Keyword spotting (KWS) is a critical component for enabling speech based...

0 Yundong Zhang, et al. ∙

research

∙ 03/08/2017

Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations

Deep convolutional neural network (CNN) inference requires significant a...

0 Liangzhen Lai, et al. ∙

Vikas Chandra

Featured Co-authors