2025 Poster "modality gap" Papers
7 papers found
Global Minimizers of Sigmoid Contrastive Loss
Kiril Bangachev, Guy Bresler, Iliyas Noman et al.
NeurIPS 2025posterarXiv:2509.18552
Mitigate the Gap: Improving Cross-Modal Alignment in CLIP
Sedigheh Eslami, Gerard de Melo
ICLR 2025poster
14
citations
Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
Jian Xiao, Zijie Song, Jialong Hu et al.
NeurIPS 2025posterarXiv:2505.12499
Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer
Ningyuan Zhang, Jie Lu, Keqiuyin Li et al.
ICLR 2025poster
1
citations
Superpowering Open-Vocabulary Object Detectors for X-ray Vision
Pablo Garcia-Fernandez, Lorenzo Vaquero, Mingxuan Liu et al.
ICCV 2025posterarXiv:2503.17071
Test-time Adaptation for Cross-modal Retrieval with Query Shift
Haobin Li, Peng Hu, Qianjun Zhang et al.
ICLR 2025posterarXiv:2410.15624
9
citations
ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models
Zixun Fang, Kai Zhu, Zhiheng Liu et al.
NeurIPS 2025posterarXiv:2506.23513