Accelerating Constrained Decoding with Token Space Compression
cs.AI
Submitted: 2026-05-28
Updated: 2026-10-01
Code: https://github.com/coli-saar/cfgzip-experiments
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- The Llama 3 Herd of Models
- Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications
- XGrammar-2: Dynamic and Efficient Structured Generation Engine for Agentic LLMs
- Constrained Decoding of Diffusion LLMs with Context-Free Grammars
- Efficient Guided Generation for Large Language Models
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems