Video

• [x] Masked Autoencoders As Spatiotemporal Learners

• [ ] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

• [ ] Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

• [ ] Flamingo: a Visual Language Model for Few-Shot Learning

• [ ] Visual Instruction Tuning

• [ ] InternVideo: General Video Foundation Models via Generative and Discriminative Learning

• [x] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

  VideoMAE: Masked Autoencoders are Data-Efficient Learners for...

• [ ] BEVT: BERT Pretraining of Video Transformers -ing

arxiv.org

• [ ] FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models

https://arxiv.org/pdf/2405.14767v2

• [ ] Never Traina from Scratch : Fair Comparision of Long-Sequence Models requires data-driven priors

https://openreview.net/pdf?id=PdaPky8MUn

• [ ] Vision Transformers Need Registers

https://openreview.net/pdf?id=2dnO3LLiJ1