Related papers: The Need for Speed: Pruning Transformers with One …

We propose a hybrid framework opPINN: physics-informed neural network (PINN) with operator learning for approximating the solution to the Fokker-Planck-Landau (FPL) equation. The opPINN framework is divided into two steps: Step 1 and Step…

CNN-LSTM based architectures have played an important role in image captioning, but limited by the training efficiency and expression ability, researchers began to explore the CNN-Transformer based models and achieved great success.…

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three…

Arbitrary text appearance poses a great challenge in scene text recognition tasks. Existing works mostly handle with the problem in consideration of the shape distortion, including perspective distortions, line curvature or other style…

Hybrid Optical Neural Networks (ONNs, typically consisting of an optical frontend and a digital backend) offer an energy-efficient alternative to fully digital deep networks for real-time, power-constrained systems. However, their adoption…

Learned image compression have attracted considerable interests in recent years. It typically comprises an analysis transform, a synthesis transform, quantization and an entropy coding model. The analysis transform and synthesis transform…

In network representation learning we learn how to represent heterogeneous information networks in a low-dimensional space so as to facilitate effective search, classification, and prediction solutions. Previous network representation…

We present FractalPINN-Flow, an unsupervised deep learning framework for dense optical flow estimation that learns directly from consecutive grayscale frames without requiring ground truth. The architecture centers on the Fractal…

This paper presents a framework for deep transfer learning, which aims to leverage information from multi-domain upstream data with a large number of samples $n$ to a single-domain downstream task with a considerably smaller number of…

Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range. Recently, Transformer family of networks has shown a more powerful learning…

Few-shot learning aims to fast adapt a deep model from a few examples. While pre-training and meta-training can create deep models powerful for few-shot generalization, we find that pre-training and meta-training focuses respectively on…

Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes. However, most of existing pruning algorithms only focus on the classification task defined on the source…

This paper introduces OptiGridML, a machine learning framework for discrete topology optimization in power grids. The task involves selecting substation breaker configurations that maximize cross-region power exports, a problem typically…

Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ…

As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of…

Recent advances in one-step generative frameworks, such as flow map models, have significantly improved the efficiency of image generation by learning direct noise-to-data mappings in a single forward pass. However, machine unlearning for…

The deployment of artificial neural networks-based optical channel equalizers on edge-computing devices is critically important for the next generation of optical communication systems. However, this is still a highly challenging problem,…

As state of the art neural networks (NNs) continue to grow in size, their resource-efficient implementation becomes ever more important. In this paper, we introduce a compression scheme that reduces the number of computations required for…

We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small…

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually…