pith. sign in

R1-v: Reinforcing super generalization ability in vision-language models with less than $3.https://github.com/Deep-Agent/R1-V, 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

EasyVideoR1: Easier RL for Video Understanding

cs.CV · 2026-04-18 · unverdicted · novelty 4.0

EasyVideoR1 delivers an optimized RL pipeline for video understanding in large vision-language models, achieving 1.47x throughput gains and aligned results on 22 benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • EasyVideoR1: Easier RL for Video Understanding cs.CV · 2026-04-18 · unverdicted · none · ref 4

    EasyVideoR1 delivers an optimized RL pipeline for video understanding in large vision-language models, achieving 1.47x throughput gains and aligned results on 22 benchmarks.