SignReasoner decomposes traffic signs into functional structure units and uses a two-stage VLM post-training pipeline to achieve state-of-the-art compositional reasoning on a new benchmark.
You only look once: Unified, real-time object de- tection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
SignReasoner: Compositional Reasoning for Complex Traffic Sign Understanding via Functional Structure Units
SignReasoner decomposes traffic signs into functional structure units and uses a two-stage VLM post-training pipeline to achieve state-of-the-art compositional reasoning on a new benchmark.
- DSAA: Dual-Stage Attribute Activation for Fine-grained Open Vocabulary Detection