- Shaking the foundations: delusions in sequence models for interaction and control: https://arxiv.org/pdf/2110.10819v1.pdf
- Understanding Dimensional Collapse in Contrastive Self-supervised Learning: https://arxiv.org/pdf/2110.09348v1.pdf
- SOFT: Softmax-free Transformer with Linear Complexity: https://arxiv.org/pdf/2110.11945v2.pdf
- Understanding How Encoder-Decoder Architectures Attend: https://arxiv.org/pdf/2110.15253v1.pdf
- Parameter Prediction for Unseen Deep Architectures: https://arxiv.org/pdf/2110.13100v1.pdf
- From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence: https://arxiv.org/pdf/2110.15245v1.pdf
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions: https://arxiv.org/pdf/2106.01798v2.pdf
- VQ-GNN: A Universal Framework to Scale-up Graph Neural Networks using Vector Quantization: https://arxiv.org/pdf/2110.14363v1.pdf
- StyleAlign: Analysis and Applications of Aligned StyleGAN Models: https://arxiv.org/pdf/2110.11323v1.pdf
- Laplace Redux – Effortless Bayesian Deep Learning: https://arxiv.org/pdf/2106.14806v2.pdf
- TorchXRayVision: A library of chest X-ray datasets and models: https://arxiv.org/pdf/2111.00595v1.pdf
- Fast Model Editing at Scale: https://arxiv.org/pdf/2110.11309v1.pdf
- Online Variational Filtering and Parameter Learning: https://arxiv.org/pdf/2110.13549v1.pdf
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers: https://arxiv.org/pdf/2110.13985v1.pdf
- Learning to Ground Multi-Agent Communication with Autoencoders: https://arxiv.org/pdf/2110.15349v1.pdf
- Applications and Techniques for Fast Machine Learning in Science: https://arxiv.org/pdf/2110.13041v1.pdf
- NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild: https://arxiv.org/pdf/2110.07604v3.pdf
- Gradient Inversion with Generative Image Prior: https://arxiv.org/pdf/2110.14962v1.pdf
- Early Convolutions Help Transformers See Better: https://arxiv.org/pdf/2106.14881.pdf
- Hierarchical Transformers Are More Efficient Language Models: https://arxiv.org/pdf/2110.13711v1.pdf
- MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining: https://arxiv.org/pdf/2110.08009v2.pdf