SOCO is a new benchmark for semantic object correspondence that provides taxonomy, annotations, and language labels to evaluate part-level understanding in vision and multimodal foundation models.
arXiv preprint arXiv:2512.15715 (2025) PRISM-CTG: A Foundation Model for CTG Analysis with Multi-View SSL 17
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
PRISM-CTG is the first large-scale foundation model for cardiotocography that uses multi-view self-supervised learning on unlabeled data to learn transferable representations, outperforming baselines on seven downstream tasks with external validation.
Rosetta Neurons in language models up to 30B and vision models up to 5B parameters scale sublinearly with size while becoming more selective and monosemantic.
ST-STORM introduces a dual-branch SSL framework that disentangles semantic content from stylistic appearance using gated latent streams, JEPA for content invariance, and adversarial constraints for style capture.
citing papers explorer
-
SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
SOCO is a new benchmark for semantic object correspondence that provides taxonomy, annotations, and language labels to evaluate part-level understanding in vision and multimodal foundation models.
-
PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL
PRISM-CTG is the first large-scale foundation model for cardiotocography that uses multi-view self-supervised learning on unlabeled data to learn transferable representations, outperforming baselines on seven downstream tasks with external validation.
-
Neuron Populations Exhibit Divergent Selectivity with Scale
Rosetta Neurons in language models up to 30B and vision models up to 5B parameters scale sublinearly with size while becoming more selective and monosemantic.
-
Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance
ST-STORM introduces a dual-branch SSL framework that disentangles semantic content from stylistic appearance using gated latent streams, JEPA for content invariance, and adversarial constraints for style capture.