arXiv Machine Learning August 21, 2026 By Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

Read the original on arXiv Machine Learning →

arXiv:2608. 20123v1 Announce Type: cross Abstract: We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without retraining.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 10

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement

arXiv:2507. 08390v5 Announce Type: replace Abstract: Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training.

By Meihua Dang, Jiaqi Han, Minkai Xu, Kai Xu, Akash Srivastava, Stefano Ermon

llms diffusion

arXiv Machine Learning

Jul 7

Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

arXiv:2607. 04780v1 Announce Type: cross Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow.

By Stanislas Strasman (SU, LPSM), Gabriel Victorino Cardoso (LPSM), Sylvain Le Corff (LPSM), Vincent Lemaire (LPSM), Antonio Ocello

diffusion safety

arXiv Machine Learning

1d ago

Theoretical Guarantees for SMC-Guided Diffusion Sampling

arXiv:2607.04780v2 Announce Type: replace-cross Abstract: Post-hoc conditioning of pretrained diffusion models can be addressed using Sequential Monte Carlo (SMC) methods. By evolving an interacting...

By Stanislas Strasman (SU, LPSM), Gabriel Victorino Cardoso (STIM), Sylvain Le Corff (LPSM), Vincent Lemaire (LPSM), Antonio Ocello

diffusion benchmarks

Hugging Face Trending Papers

Jul 6

Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow. This paper develops a non-asymptotic error analysis for such SMC samplers.

diffusion safety

arXiv Machine Learning

1d ago

FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models

arXiv:2609.35947v1 Announce Type: new Abstract: Many inference-time tasks for pretrained discrete diffusion models and diffusion language models reduce to drawing samples from a tilted version of the...

By Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff, Jiequn Han, Lexing Ying

llms diffusion benchmarks

arXiv Machine Learning

Jul 28

Learning Sampling Parameters for Diffusion Models

arXiv:2607. 23488v1 Announce Type: new Abstract: Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules.

By Arisrei Lim, Yossi Gandelsman

llms diffusion reinforcement-learning multimodal

One email a morning, machine-written

Related stories

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement

Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

Theoretical Guarantees for SMC-Guided Diffusion Sampling

Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models

Learning Sampling Parameters for Diffusion Models