Search Results for author:
Found 34 papers, 20 papers with code
Tiny Machine Learning: Progress and Futures
By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scope of AI applications and enable ubiquitous intelligence.
VILA: On Pre-training for Visual Language Models
Visual language models (VLMs) rapidly progressed with the recent success of large language models.
Ranked #21 on
Visual Question Answering
on MM-Vet
Rule-Guided Joint Embedding Learning over Knowledge Graphs
Recent studies focus on embedding learning over knowledge graphs, which map entities and relations in knowledge graphs into low-dimensional vector spaces.
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
On-device learning and efficient fine-tuning enable continuous and privacy-preserving customization (e. g., locally fine-tuning large language models on personalized data).
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Large language models (LLMs) have shown excellent performance on various tasks, but the astronomical model size raises the hardware barrier for serving (memory size) and slows down token generation (memory bandwidth).
Offsite-Tuning: Transfer Learning without Full Model
In this paper, we propose Offsite-Tuning, a privacy-preserving and efficient transfer learning framework that can adapt billion-parameter foundation models to downstream data without access to the full model.
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs.
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
With about $1\%$-area edits, SIGE accelerates DDPM by $3. 0\times$ on NVIDIA RTX 3090 and $4. 6\times$ on Apple M1 Pro GPU, Stable Diffusion by $7. 2\times$ on 3090, and GauGAN by $5. 6\times$ on 3090 and $5. 2\times$ on M1 Pro GPU.
On-Device Training Under 256KB Memory
To reduce the memory footprint, we propose Sparse Update to skip the gradient computation of less important layers and sub-tensors.
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition.
Memory-efficient Patch-based Inference for Tiny Deep Learning
We further propose receptive field redistribution to shift the receptive field and FLOPs to the later stage and reduce the computation overhead.
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
We further propose network redistribution to shift the receptive field and FLOPs to the later stage and reduce the computation overhead.
Network Augmentation for Tiny Deep Learning
We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks.
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device
Secondly, TSM has high efficiency; it achieves a high frame rate of 74fps and 29fps for online video recognition on Jetson Nano and Galaxy Note8.
Anycost GANs for Interactive Image Synthesis and Editing
Generative adversarial networks (GANs) have enabled photorealistic image synthesis and editing.
Hardware-Centric AutoML for Mixed-Precision Quantization
Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures.
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely.
Ranked #1 on
Robust 3D Semantic Segmentation
on SemanticKITTI-C
MCUNet: Tiny Deep Learning on IoT Devices
Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones.
Differentiable Augmentation for Data-Efficient GAN Training
Furthermore, with only 20% training data, we can match the top performance on CIFAR-10 and CIFAR-100.
Ranked #1 on
Image Generation
on CIFAR-10 (20% data)
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
However, training this quantization-aware accuracy predictor requires collecting a large number of quantized <model, accuracy> pairs, which involves quantization-aware finetuning and thus is highly time-consuming.
Lite Transformer with Long-Short Range Attention
For language modeling, Lite Transformer achieves 1. 8 lower perplexity than the transformer at around 500M MACs.
Ranked #36 on
Machine Translation
on WMT2014 English-French
GAN Compression: Efficient Architectures for Interactive Conditional GANs
Directly applying existing compression methods yields poor performance due to the difficulty of GAN training and the differences in generator architectures.
Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
With such hardware-aware model design, we are able to scale up the training on Summit supercomputer and reduce the training time on Kinetics dataset from 49 hours 55 minutes to 14 minutes 13 seconds, achieving a top-1 accuracy of 74. 0%, which is 1. 6x and 2. 9x faster than previous 3D video models with higher accuracy.
Design Automation for Efficient Deep Learning Computing
Moreover, we shorten the design cycle by 200x than previous work, so that we can afford to design specialized neural network models for different hardware platforms.
Defensive Quantization: When Efficiency Meets Robustness
This paper aims to raise people's awareness about the security of the quantized models, and we designed a novel quantization methodology to jointly optimize the efficiency and robustness of deep learning models.
Joint Monocular 3D Vehicle Detection and Tracking
The framework can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform.
Ranked #12 on
Multiple Object Tracking
on KITTI Tracking test
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures.
TSM: Temporal Shift Module for Efficient Video Understanding
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost.
Ranked #2 on
3D Action Recognition
on Assembly101
Adaptive Mixture of Low-Rank Factorizations for Compact Neural Modeling
Modern deep neural networks have a large amount of weights, which make them difficult to deploy on computation constrained devices such as mobile phones.
Reinforcement Learning from Imperfect Demonstrations
We propose a unified reinforcement learning algorithm, Normalized Actor-Critic (NAC), that effectively normalizes the Q-function, reducing the Q-values of actions unseen in the demonstration data.
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets.
Runtime Neural Pruning
In this paper, we propose a Runtime Neural Pruning (RNP) framework which prunes the deep neural network dynamically at the runtime.
Learning Discriminative Aggregation Network for Video-Based Face Recognition
In this paper, we propose a discriminative aggregation network (DAN) for video face recognition, which aims to integrate information from video frames effectively and efficiently.
Consistent-Aware Deep Learning for Person Re-Identification in a Camera Network
In this paper, we propose a consistent-aware deep learning (CADL) framework for person re-identification in a camera network.
