Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement
arXiv:2603.24208v1 Announce Type: cross Abstract: Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While…
Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG
arXiv:2603.23562v1 Announce Type: cross Abstract: Synthetic data augmentation helps language models learn new knowledge in data-constrained domains. However, naively scaling…
A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula
arXiv:2603.24202v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for improving large language models beyond…
CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
arXiv:2603.23559v1 Announce Type: cross Abstract: GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that…