Cover Image for Attention Alternatives & Scaling Context Windows (w/ Innovation Endeavors & Cerebral Valley)
Cover Image for Attention Alternatives & Scaling Context Windows (w/ Innovation Endeavors & Cerebral Valley)
161 Went

Attention Alternatives & Scaling Context Windows (w/ Innovation Endeavors & Cerebral Valley)

Hosted by Davis Treybig & 3 others
Registration
Past Event
Welcome! To join the event, please register below.
About Event

Recently, there has been substantial interest in ways to further scale LLM context windows by getting around the quadratic scaling of attention, such as Mamba, Striped Hyena, State Space Models, and Monarch Mixer.

Come join us for an evening where we will discuss this emerging line of research.

We will kick things off with presentations by some of the leading researchers exploring attention alternatives and sub-quadratic scaling of attention windows, and then we'll have an open happy hour.

Presentations by:

  1. Karan Goel (CEO of Cartesia AI) - The history and future of State Space Models

  2. Jacob Buckman (Manifest AI) - Drawbacks & Opportunities for Linear Transformers

  3. Bailin Wang (MIT) - Gated Linear Attention Transformers with Hardware-Efficient Training

  4. Michael Poli - StripedHyena

  5. Eugene Cheah - RWKV

Hosted by Innovation Endeavors and Cerebral Valley

Location
Shack15
1, Ferry Building, Suite 201, San Francisco, CA 94111, USA
161 Went