pith. sign in

Title resolution pending

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

2 Pith papers citing it

fields

cs.CV 1 cs.RO 1

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

cs.CV · 2026-05-20 · unverdicted · novelty 5.0

Lens is a 3.8B-parameter text-to-image model that reaches competitive or superior performance to >6B-parameter systems using 19.3% of the training compute of Z-Image through a densely captioned 800M dataset, multi-resolution batching, semantic VAE, strong language encoder, RL fine-tuning, and 4-step

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models cs.CV · 2026-05-20 · unverdicted · none · ref 19

    Lens is a 3.8B-parameter text-to-image model that reaches competitive or superior performance to >6B-parameter systems using 19.3% of the training compute of Z-Image through a densely captioned 800M dataset, multi-resolution batching, semantic VAE, strong language encoder, RL fine-tuning, and 4-step