Search Results for author:
Found 17 papers, 5 papers with code
Multi-label feature selection based on binary hashing learning and dynamic graph constraints
To overcome these limitations, this study introduces a novel multi-label feature selection method called Binary Hashing and Dynamic Graph Constraint (BHDG), the first method to integrate binary hashing into multi-label learning.
Hamming Attention Distillation: Binarizing Keys and Queries for Efficient Long-Context Transformers
HAD achieves just $\mathbf{1. 78}\%$ performance losses on GLUE compared to $9. 08\%$ in state-of-the-art binarization work, and $\mathbf{2. 5}\%$ performance losses on ImageNet compared to $12. 14\%$, all while targeting custom hardware with a $\mathbf{79}\%$ area reduction and $\mathbf{87}\%$ power reduction compared to its standard attention counterpart.
A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models
The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language processing and moving towards multi-modal functionality.
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM).
A novel feature selection framework for incomplete data
Existing methods address this challenge by first employing imputation methods to complete the incomplete data and then conducting feature selection based on the imputed data.
Iterative missing value imputation based on feature importance
Existing imputation methods estimate the missing parts based on the observed values in the original feature space, and they treat all features as equally important during data completion, while in fact different features have different importance.
Accelerating Generic Graph Neural Networks via Architecture, Compiler, Partition Method Co-Design
However, designing GNN accelerators faces two fundamental challenges: the high bandwidth requirement of GNN models and the diversity of GNN models.
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
VDD: Varied Drone Dataset for Semantic Segmentation
Semantic segmentation of drone images is critical for various aerial vision tasks as it provides essential semantic details to understand scenes on the ground.
Ranked #1 on
Semantic Segmentation
on VDD
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN).
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
Efficient Adaptive Activation Rounding for Post-Training Quantization
To deal with the runtime overhead, we use a coarse-grained version of the border function.
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.
Dual-side Sparse Tensor Core
We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core.
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Network pruning can reduce the high computation cost of deep neural network (DNN) models.
Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration
We propose Simultaneous Multi-mode Architecture (SMA), a novel architecture design and execution model that offers general-purpose programmability on DNN accelerators in order to accelerate end-to-end applications.
Adversarial Defense Through Network Profiling Based Path Extraction
Recently, researchers have started decomposing deep neural network models according to their semantics or functions.
