Search Results for author:
Found 41 papers, 23 papers with code
DataMix: Efficient Privacy-Preserving Edge-Cloud Inference
Third, our solution is extit{efficient} on the edge since the majority of the workload is delegated to the cloud, and our mixing and de-mixing processes introduce very few extra computations.
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
On average, LServe accelerates LLM prefilling by up to 2. 9x and decoding by 1. 3-2. 1x over vLLM, maintaining long-context accuracy.
NVILA: Efficient Frontier Visual Language Models
This paper introduces NVILA, a family of open VLMs designed to optimize both efficiency and accuracy.
Ranked #5 on
Video Question Answering
on NExT-QA
VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge
In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models.
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
We introduce the long-context Multi-Modal Sequence Parallelism (MM-SP) system that efficiently parallelizes long video training and inference, enabling 2M context length training on 256 GPUs without any gradient checkpointing.
Ranked #8 on
Video Question Answering
on NExT-QA
Sparse Refinement for Efficient High-Resolution Semantic Segmentation
Finally, it leverages a gated ensembler to apply these sparse refinements to the initial coarse predictions.
LidarDM: Generative LiDAR Simulation in a Generated World
We present LidarDM, a novel LiDAR generative model capable of producing realistic, layout-aware, physically plausible, and temporally coherent LiDAR videos.
Point Transformer V3: Simpler Faster Stronger
This paper is not motivated to seek innovation within the attention mechanism.
StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation.
Point Transformer V3: Simpler, Faster, Stronger
This paper is not motivated to seek innovation within the attention mechanism.
Ranked #1 on
3D Semantic Segmentation
on ScanNet++
(using extra training data)
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
On top of this, we design the Sparse Autotuner, which extends the design space of existing sparse convolution libraries and searches for the best dataflow configurations for training and inference workloads.
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048.
MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models
Despite tremendous advancements in bird's-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information (such as occlusion or limited coverage).
CA-CentripetalNet: A novel anchor-free deep learning framework for hardhat wearing detection
Automatic hardhat wearing detection can strengthen the safety management in construction sites, which is still challenging due to complicated video surveillance scenes.
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
High-resolution images enable neural networks to learn richer visual representations.
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Transformer, as an alternative to CNN, has been proven effective in many modalities (e. g., texts and images).
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Multi-sensor fusion is essential for an accurate and reliable autonomous driving system.
Ranked #4 on
3D Object Detection
on nuScenes
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.
PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
3D neural networks are widely used in real-world applications (e. g., AR/VR headsets, self-driving cars).
TorchSparse: Efficient Point Cloud Inference Engine
TorchSparse directly optimizes the two bottlenecks of sparse convolution: irregular computation and data movement.
VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles
Simulation has the potential to transform the development of robust algorithms for mobile agents deployed in safety-critical scenarios.
LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets.
Efficient and Robust LiDAR-Based End-to-End Navigation
On the other hand, increasing the robustness of these systems is also critical; however, even estimating the model's uncertainty is very challenging due to the cost of sampling-based methods.
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
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.
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
To enable low-latency inference on resource-constrained hardware platforms, we propose to design Hardware-Aware Transformers (HAT) with neural architecture search.
Ranked #21 on
Machine Translation
on WMT2014 English-French
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 #37 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.
Point-Voxel CNN for Efficient 3D Deep Learning
The computation cost and memory footprints of the voxel-based models grow cubically with the input resolution, making it memory-prohibitive to scale up the resolution.
Ranked #1 on
3D Object Detection
on KITTI Pedestrian Hard val
Deep Leakage from Gradients
Exchanging gradients is a widely used method in modern multi-node machine learning system (e. g., distributed training, collaborative learning).
Modeling Parts, Structure, and System Dynamics via Predictive Learning
Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future.
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.
Unsupervised Discovery of Parts, Structure, and Dynamics
Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future.
Learning to Exploit Stability for 3D Scene Parsing
We first show that applying physics supervision to an existing scene understanding model increases performance, produces more stable predictions, and allows training to an equivalent performance level with fewer annotated training examples.
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.
Physical Primitive Decomposition
As annotated data for object parts and physics are rare, we propose a novel formulation that learns physical primitives by explaining both an object's appearance and its behaviors in physical events.
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.
Machine Learning for Building Energy and Indoor Environment: A Perspective
It is indicated that the theories and applications of machine learning method in the field of energy conservation and indoor environment are not mature, due to the difficulty of the determination for model structure with better prediction.
Performance Prediction and Optimization of Solar Water Heater via a Knowledge-Based Machine Learning Method
This Chapter consists of: i) Comparative studies on varieties of machine learning models (artificial neural networks (ANNs), support vector machine (SVM) and extreme learning machine (ELM)) to predict the performances of SWHs; ii) Development of an ANN-based software to assist the quick prediction and iii) Introduction of a computational HTS method to design a high-performance SWH system.
