State of AI Models

3 papers · avg viability 4.0

Download CSV View topic page

Top papers

Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts(5.0)
The Information Geometry of Softmax: Probing and Steering(5.0)
Poly-attention: a general scheme for higher-order self-attention(2.0)