pith. sign in

Subgen: Token generation in sublinear time and memory

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.DS 1 cs.LG 1

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

Nearly Optimal Attention Coresets

cs.DS · 2026-05-07 · unverdicted · novelty 8.0

ε-coresets for attention exist of size O(√d e^{ρ+o(ρ)}/ε) for unit-norm keys/values and queries of norm ≤ρ, nearly matching the Ω(√d e^ρ/ε) lower bound.

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

cs.LG · 2025-04-28 · unverdicted · novelty 6.0

TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a factor of approximately 2.7.

citing papers explorer

Showing 2 of 2 citing papers.

  • Nearly Optimal Attention Coresets cs.DS · 2026-05-07 · unverdicted · none · ref 52

    ε-coresets for attention exist of size O(√d e^{ρ+o(ρ)}/ε) for unit-norm keys/values and queries of norm ≤ρ, nearly matching the Ω(√d e^ρ/ε) lower bound.

  • TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate cs.LG · 2025-04-28 · unverdicted · none · ref 64

    TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a factor of approximately 2.7.