Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
- Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
- Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
- XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- Discrete Feynman-Kac Correctors
- Automata-based constraints for language model decoding
- Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
- Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
- Large Language Diffusion Models
- Grammar-Aligned Decoding
- Simple and Effective Masked Diffusion Language Models
- DINGO: Constrained Inference for Diffusion LLMs
- SynCode: LLM Generation with Grammar Augmentation
- Efficient Guided Generation for Large Language Models
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
- Dream-Coder 7B: An Open Diffusion Language Model for Code
- Dream 7B: Diffusion Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks