NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference Paper • 2609.01657 • Published 7 days ago • 25
How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data Paper • 2604.13977 • Published Apr 15 • 2