← all notes

Cool ML TBR

tbr

  1. Attention Sinks https://arxiv.org/pdf/2309.17453
  2. Prioritized Level Replay https://arxiv.org/pdf/2010.03934
  3. Scenic: A Language for Scenario Specification and Scene Generation https://arxiv.org/pdf/1809.09310
  4. Mamba: Linear-Time Sequence Modelling With Selective State Spaces
  5. Infinite Photorealistic Worlds using Procedural Generation https://arxiv.org/pdf/2306.09310
  6. DAGGER - https://arxiv.org/abs/1011.0686
  7. On-Policy Distillation- https://thinkingmachines.ai/blog/on-policy-distillation