conftrace_

multimodal task

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

compositional image captioning (1) region-based description (1) pairwise losses (1) poly-matching cost (1) sample-efficient pretraining (1) region description (1) multi-marginal optimal transport (1) cognitive evaluation (1) vision-language modeling (1) compositional reasoning (1)

Papers

BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models CVPR 2026 FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity CVPR 2025 Contrasting Multiple Representations with the Multi-Marginal Matching Gap ICML 2024