World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representations used across tasks and action policies. Existing attacks on these models opti...
Xuan-Yu Lu, Feng-Qing Jiang, Kai-Yuan Zheng et al.· 0 citations
This work presents MidTool, an open corpus construction pipeline for agentic tool-use mid-training that combines large-scale web, PDF, and code data with synthesized supervision from real-world tool APIs, MCP skills, and document-grounded workflows and suggests that general tool use, like other important LLM capabiliti...
Fengqing Jiang, Yi-Te Wang, Bo-Yi Liu et al.· 0 citations
Student-Centric Answer Sampling (SCAS) is proposed, a framework that selects from verified teacher-generated answers according to their estimated student-centric learning cost and is derived by a token-wise gradient decomposition and used to guide answer selection during training.
Zhengyu Hu, Zheyuan Xiao, Linxin Song et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.