CDM amortizes SMC inference for reward-tilted discrete diffusion by training a parameterized twist function on contrastive samples with closed-form kernels.
Probabilistic inference in language models via twisted sequential monte carlo
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Sequential Monte Carlo sampling from a reward-augmented sequence distribution improves LLM performance on HumanEval by up to 54.9% and MATH500 by up to 8.8%, outperforming standard sampling and GRPO.
Proposes Latent Interacting Particle Systems with an efficient parameterization of twist potentials to enable approximate posterior inference for coupled continuous-time hidden Markov models via twisted sequential Monte Carlo, demonstrated on a latent SIRS graph model and real wildfire data.
The Twisted-Path Particle Filter parameterizes twisting functions via neural networks and optimizes them against a path-measure KL divergence to improve continuous-time particle filtering.
citing papers explorer
-
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
CDM amortizes SMC inference for reward-tilted discrete diffusion by training a parameterized twist function on contrastive samples with closed-form kernels.
-
Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
Sequential Monte Carlo sampling from a reward-augmented sequence distribution improves LLM performance on HumanEval by up to 54.9% and MATH500 by up to 8.8%, outperforming standard sampling and GRPO.
-
Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
Proposes Latent Interacting Particle Systems with an efficient parameterization of twist potentials to enable approximate posterior inference for coupled continuous-time hidden Markov models via twisted sequential Monte Carlo, demonstrated on a latent SIRS graph model and real wildfire data.
-
Guidance for twisted particle filter: a continuous-time perspective
The Twisted-Path Particle Filter parameterizes twisting functions via neural networks and optimizes them against a path-measure KL divergence to improve continuous-time particle filtering.