Search papers, labs, and topics across Lattice.
尾 Xiaohongshu Inc, Fudan University, Tongji University, 未 University of California
3
0
6
Frontier models can't build playable games in one shot, but a closed-loop system using GUI agents to playtest and refine code achieves a 66.8% success rate, proving that game generation needs to be a conversation, not a translation.
Personal agents can now dynamically synthesize UIs directly from dialogue context, achieving state-of-the-art results without relying on explicit schemas.
Watermarking agent memories is now possible without performance degradation or reliance on logs, enabling snapshot-only attribution even after memory migration or leakage.
