pith. sign in

How to evaluate the generalization of detection? a benchmark for comprehensive open-vocabulary detection

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

2 Pith papers citing it

citation-role summary

dataset 1

citation-polarity summary

fields

cs.CV 2

years

2025 2

verdicts

UNVERDICTED 2

roles

dataset 1

polarities

use dataset 1

representative citing papers

GRIT: Teaching MLLMs to Think with Images

cs.CV · 2025-05-21 · unverdicted · novelty 7.0

GRIT introduces a grounded reasoning paradigm for MLLMs where reasoning chains interleave text and bounding boxes, trained via GRPO-GR reinforcement learning on as few as 20 examples without annotations.

citing papers explorer

Showing 2 of 2 citing papers.

  • GRIT: Teaching MLLMs to Think with Images cs.CV · 2025-05-21 · unverdicted · none · ref 28

    GRIT introduces a grounded reasoning paradigm for MLLMs where reasoning chains interleave text and bounding boxes, trained via GRPO-GR reinforcement learning on as few as 20 examples without annotations.

  • VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model cs.CV · 2025-04-10 · unverdicted · none · ref 54

    VLM-R1 applies R1-style RL using rule-based rewards on visual tasks with clear ground truth to achieve competitive performance and superior generalization over SFT in vision-language models.