EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
Puzzle Curriculum GRPO for Vision-Centric Reasoning.arXiv preprint arXiv:2512.14944, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
AVIS is an adaptive policy that jointly scales visual context via key-based token pruning and reasoning via difficulty-predicted self-consistency to improve the accuracy-compute curve on image and video tasks.
citing papers explorer
-
EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
-
AVIS: Adaptive Test-Time Scaling for Vision-Language Models
AVIS is an adaptive policy that jointly scales visual context via key-based token pruning and reasoning via difficulty-predicted self-consistency to improve the accuracy-compute curve on image and video tasks.