VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
Ziyan Jiang, Meng, Rui, Xinyi Yang, Semih Yavuz, Yingbo Zhou, Wenhu Chen
De quem é
- Salesforceafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPTBeihang University · 1.211 citações
- RLHF Workflow: From Reward Modeling to Online RLHFSalesforce · 438 citações
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and DatasetNew York University · 437 citações
- A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?McGill University · 363 citações
- ULIP-2: Towards Scalable Multimodal Pre-Training for 3D UnderstandingSalesforce · 351 citações
- Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsSalesforce · 314 citações