most citedPhi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

7 citations · 7 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

Miaosen Zhang, Yishan Liu, Shuxia Lin +8

Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use…