Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models Paper • 2504.15271 • Published 7 days ago • 63
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models Paper • 2504.15271 • Published 7 days ago • 63
nvidia/Llama-Nemotron-Post-Training-Dataset Viewer • Updated about 19 hours ago • 3.91M • 8.28k • 429
Token-Efficient Long Video Understanding for Multimodal LLMs Paper • 2503.04130 • Published Mar 6 • 94
QLIP Collection QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated 5 days ago • 8
QLIP Collection QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated 5 days ago • 8