🛰️ Daily AI Frontier
‹ back to 2026-08-22

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

Research LLMs & Foundation Models

Ranking

Overall 79
Content 95
Popularity 42

Observed public metrics from 1 member.

Representative image for Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

Merged summary

TL;DR - This paper introduces nested sequential Monte Carlo methods for steering discrete diffusion language models toward sequence-level rewards at inference time, without retraining. The methods address biases and sampling weaknesses in prior approaches and improve toxicity and fluency control in the reported experiments.

  • Formulates nested SMC (NSMC) and fully adapted nested SMC (FA-NSMC) for Feynman–Kac steering.
  • Identifies and corrects errors in earlier formulations that produce biased final estimates.
  • Targets limitations of best-of-(n) sampling and bootstrap SMC, including overoptimism and weight degeneracy.
  • NSMC and FA-NSMC consistently outperform both baselines on toxicity and fluency steering tasks.

Sources (1)

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

arXiv stat.ML Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth 2026-08-20 arXiv:2608.20123
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-12 14:22:24.521718 UTC

TL;DR - This paper introduces nested sequential Monte Carlo methods for steering discrete diffusion language models toward sequence-level rewards at inference time, without retraining. The methods address biases and sampling weaknesses in prior approaches and improve toxicity and fluency control in the reported experiments.

  • Formulates nested SMC (NSMC) and fully adapted nested SMC (FA-NSMC) for Feynman–Kac steering.
  • Identifies and corrects errors in earlier formulations that produce biased final estimates.
  • Targets limitations of best-of-(n) sampling and bootstrap SMC, including overoptimism and weight degeneracy.
  • NSMC and FA-NSMC consistently outperform both baselines on toxicity and fluency steering tasks.
item →