GraSP-VL turns frozen VLM embedding length into a controllable semantic granularity interface via a learned shared prefix transform that creates a Semantic Matryoshka structure.
Proceedings of the 38th International Conference on Machine Learning , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Mixing real UAV imagery with 2101 AI-generated image-mask pairs improves semantic segmentation F1 scores for fine-grained forest species by over 15 percentage points overall and up to 30 points for rare classes.
citing papers explorer
-
GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations
GraSP-VL turns frozen VLM embedding length into a controllable semantic granularity interface via a learned shared prefix transform that creates a Semantic Matryoshka structure.
-
Leveraging Image Generators to Address Training Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping
Mixing real UAV imagery with 2101 AI-generated image-mask pairs improves semantic segmentation F1 scores for fine-grained forest species by over 15 percentage points overall and up to 30 points for rare classes.