2 papers
cs.CV2026
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Sudong Wang, Weiquan Huang, Xiaomin Yu +9
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiab…
cs.CV2025
DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
Li Ren, Chen Chen, Liqiang Wang +1
Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnabl…