Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation
Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fine-Tuning (SFT), which often leads to surface-level pattern matching and degrades general capabilities. While Reinforcement Learning with Verifiable Rewards (RLVR) offers a...
Yi-Rong Zeng, Sai Zhang, Yu-Xian Wang et al.
· 0 citations