A Geometry-Aware Message Passing Neural Network for Modeling Aerodynamics over Airfoils
By Kate Martin
Posted on: December 13, 2024
Computational modeling of aerodynamics is a key problem in aerospace engineering, often involving flows interacting with solid objects such as airfoils. Deep surrogate models have emerged as purely data-driven approaches that learn direct mappings from simulation conditions to solutions based on eit...
GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia
By Kate Martin
Posted on: December 11, 2024
GraphNeuralNetworks.jl is an open-source framework for deep learning on graphs, written in the Julia programming language. It supports multiple GPU backends, generic sparse or dense graph representations, and offers convenient interfaces for manipulating standard, heterogeneous, and temporal graphs ...
Federated Learning in Mobile Networks: A Comprehensive Case Study on Traffic Forecasting
By Kate Martin
Posted on: December 09, 2024
The increasing demand for efficient resource allocation in mobile networks has catalyzed the exploration of innovative solutions that could enhance the task of real-time cellular traffic prediction. Under these circumstances, federated learning (FL) stands out as a distributed and privacy-preserving...
GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction
By Kate Martin
Posted on: December 09, 2024
3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scen...
VisionZip: Longer is Better but Not Necessary in Vision Language Models
By Javier Vásquez
Posted on: December 09, 2024
Recent advancements in vision-language models have enhanced performance by increasing the length of visual tokens, making them much longer than text tokens and significantly raising computational costs. However, we observe that the visual tokens generated by popular vision encoders, such as CLIP and...
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
By Javier Vásquez
Posted on: December 06, 2024
We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction framework with an infinite-vocabulary tokenizer & classifier and ...
XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation
By Kate Martin
Posted on: December 04, 2024
Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture, quantization techniques, and training recipes have significantly enhanc...
Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization, resulting in considerable inference overhead in real-world applications. In this work, we present TinyFusion, a depth pruning method designed to remove redundant layer...
