LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators

cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

Comments: 29 pages, 7 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• Classifier-Free Diffusion Guidance
• Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
• Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
• Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
• Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
• Stream-T1: Test-Time Scaling for Streaming Video Generation
• Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
• Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks