Asia
Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
When training deep neural networks, a model's generalization error is often observed to follow a power scaling law dependent both on the model size and the
TowardsVideoTextVisualQuestionAnswering: BenchmarkandBaseline
Therearealready sometext-based visualquestion answering(TextVQA) benchmarks for developing machine's ability to answer questions based on texts in imagesinrecentyears.
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
Codes and the dataset are available on the website.
Memory-oriented Decoder for Light Field Salient Object Detection
Miao Zhang, Jingjing Li, JI WEI, Yongri Piao, Huchuan Lu
Neural Information Processing Systems http://nips.cc/
Functional Adversarial Attacks
Neural Information Processing Systems http://nips.cc/
SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
Time series analysis is widely used in extensive areas.
A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
Jeffrey Chan, Valerio Perrone, Jeffrey Spence, Paul Jenkins, Sara Mathieson, Yun Song
Neural Information Processing Systems http://nips.cc/
