DailyPapers (@HuggingPapers)
@HuggingPapers
Tweeting interesting papers submitted at
Submit your own at and link models/datasets/demos to it!
4 正在关注 18K 粉丝
Microsoft just released SkillOpt
Train agent skills like neural networks — in text space, without touching model weights. Best or tied-best in 52/52 settings across 6 benchmarks and 7 models.
显示更多
ByteDance releases Lance, a 3B unified multimodal model
One framework for image/video understanding, generation, and editing. With only 3B active parameters, it beats 7B+ models on benchmarks thanks to multi-task synergy and specialized MoE pathways.
显示更多
