CSRS improves MLLM self-evolution stability by using retracing mechanisms and softened continuous rewards instead of majority voting, reaching SOTA on geometric reasoning benchmarks like MathVision.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling
CSRS improves MLLM self-evolution stability by using retracing mechanisms and softened continuous rewards instead of majority voting, reaching SOTA on geometric reasoning benchmarks like MathVision.