- Covariate Shift in High-Dimensional Random Feature Regression: https://arxiv.org/pdf/2111.08234v1.pdf
- Improving Transferability of Representations via Augmentation-Aware Self-Supervision: https://arxiv.org/pdf/2111.09613v1.pdf
- GFlowNet Foundations: https://arxiv.org/pdf/2111.09266v1.pdf
- Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability: https://arxiv.org/pdf/2111.10752v1.pdf
- Benchmarking Detection Transfer Learning with Vision Transformers: https://arxiv.org/pdf/2111.11429v1.pdf
- Improved Knowledge Distillation via Adversarial Collaboration: https://arxiv.org/pdf/2111.14356v1.pdf
- End-to-End Referring Video Object Segmentation with Multimodal Transformers: https://arxiv.org/pdf/2111.14821v1.pdf
- On the Integration of Self-Attention and Convolution: https://arxiv.org/pdf/2111.14556v1.pdf
- Florence: A New Foundation Model for Computer Vision: https://arxiv.org/pdf/2111.11432v1.pdf
- A Survey Of Generalisation In Deep Reinforcement Learning: https://arxiv.org/pdf/2111.09794v1.pdf
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields: https://arxiv.org/pdf/2111.12077v2.pdf
- PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers: https://arxiv.org/pdf/2111.12710v1.pdf
- Neural Fields in Visual Computing and Beyond: https://arxiv.org/pdf/2111.11426v3.pdf
- Sparse is Enough in Scaling Transformers: https://arxiv.org/pdf/2111.12763v1.pdf
- Dynamic Graph Representation Learning Via Graph Transformer Networks: https://arxiv.org/pdf/2111.10447v1.pdf
- Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters: https://arxiv.org/pdf/2111.05897v3.pdf
- MetaFormer is Actually What You Need for Vision: https://arxiv.org/pdf/2111.11418v2.pdf
- VIOLET: End-to-End Video-Language Transformers with Masked Visual-token Modeling: https://arxiv.org/pdf/2111.12681v1.pdf
- XLS-R: Self-Supervised Cross-Lingual Speech Representation Learning At Scale: https://arxiv.org/pdf/2111.09296v2.pdf
- True Few-Shot Learning with Prompts – A Real-World Perspective: https://arxiv.org/pdf/2111.13440v1.pdf
- Efficient Decompositional Rule Extraction for Deep Neural Networks: https://arxiv.org/pdf/2111.12628v1.pdf
- State-space deep Gaussian processes with applications: https://arxiv.org/pdf/2111.12604v1.pdf
- μNCA: Texture Generation with Ultra-Compact Neural Cellular Automata: https://arxiv.org/pdf/2111.13545v1.pdf
- DeBERTaV3: Improving DeBERTa using ELECTRA- Style Pre-Training with Gradient-Disentangled Embedding Sharing: https://arxiv.org/pdf/2111.09543v1.pdf
- DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning: https://arxiv.org/pdf/2111.12062v1.pdf