Pre^3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation

Aug 1, 2025·

Junyi Chen

,

Shihao Bai

,

Zaijun Wang

,

Siyu Wu

,

Chuheng Du

,

Hailong Yang

Ruihao Gong

📧 Corresponding Author

,

Shengzhong Liu

📧 Corresponding Author

,

Fan Wu

,

Guihai Chen

· 0 min read

Cite

Authors

Ruihao Gong

---

← TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference Systems Jan 1, 2026

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints Apr 1, 2025 →