VisHarness learns a reinforcement-learned policy to harness specialized visual experts via multi-turn interactions and dynamic visual memory archiving, outperforming general models on four visual reasoning benchmarks.
Empowering segmentation ability to multi-modal large language models.arXiv preprint arXiv:2403.14141, 2024
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
-
Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
VisHarness learns a reinforcement-learned policy to harness specialized visual experts via multi-turn interactions and dynamic visual memory archiving, outperforming general models on four visual reasoning benchmarks.