DailyPapers
@HuggingPapers
Tweeting interesting papers submitted at
Submit your own at and link models/datasets/demos to it!
加入 March 2025
4 正在关注 20.4K 粉丝
V-Zero: answer-label-free visual reasoning
It uses on-policy distillation with contrastive evidence gating.
It trains 5x faster than SFT and 10x faster than RL.
4B model is on Hugging Face.
显示更多
