arXiv:2409.18868
Individuation in Neural Models with and without Visual Grounding
원문 초록
We show differences between a language-and-vision model CLIP and two text-only models - FastText and SBERT - when it comes to the encoding of individuation information. We study latent representations that CLIP provides for substrates, granular aggregates, and various numbers of objects. We demonstrate that CLIP embeddings capture quantitative differences in individuation better than models trained on text-only data. Moreover, the individuation hierarchy we deduce from the CLIP embeddings agrees with the hierarchies proposed in linguistics and cognitive science.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GTA1: GUI Test-time Scaling Agent
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs
Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.