World Action Models (WAMs) have emerged as a promising paradigm for generalizable robot control. Despite the growing number of WAM systems, existing works often introduce unified systems that bundle together multiple design choices, such as architecture and training strategy, making it difficult to isolate individual c...
Chao Tang, Haoqing Wang, Zi-Lang Cen et al.· 0 citations
The RLVR across domains exhibits small mutual interferences, and reasoning-intensive domains have mutually synergistic effects, and the internal mechanisms from the perspectives of information constraints, model prediction behavior and self-verification are analyzed.
Haoqing Wang, Xiang Long, Ziheng Li et al.· arXiv.org· 11 citations
FaithEyes, a multi-agent self-judging framework that uses a VLM to judge whether each process image helps answer the question and designs a multi-agent framework where the model itself serves as a subagent to judge the tool calls from the main agent, eliminating any dependence on external models at inference.
Mage-VL is presented, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction and establishes AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes.
