multimodal 5
- Sentence Transformers v6.1 Makes Input Order Part of Your Index
- Gemini Native Visual Generation: Architecture and Typography in Google Image Models
- ColPali: Efficient Document Retrieval via Vision Language Models and Late Interaction
- Vision-Language Architectures: Cross-Attention vs Autoregressive Fusion
- GPT-4o Architecture: Omni-Modal Foundation Models and Low-Latency Native Audio