vix.ing · top · new · best · stats · spec

Christos Perivolaropoulos

  1. Round and Round We Go! What makes Rotary Positional Encodings useful?
    2024/10/08 by Federico Barbero, Barbero, Federico, Alex Vitvitskyi +7 · 4 voices · 23 citations
    Computer Science · #Constraint Satisfaction and Optimization #Natural Language Processing Techniques #Speech and dialogue systems #cs.CL #cs.LG
  2. Why do LLMs attend to the first token?
    2025/04/03 by Federico Barbero, Barbero, Federico, Álvaro Arroyo +11 · 3 voices · 30 citations
    #cs.CL
  3. Softmax is not Enough (for Sharp Size Generalisation)
    2024/10/01 by Petar Veličković, Veličković, Petar, Christos Perivolaropoulos +5 · 6 voices · 8 citations
    Decision Sciences · #Scientific Computing and Data Management #cs.AI #cs.IT #cs.LG