We have 7 of 7 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Efficient sampling from Bayesian posterior distributions in high dimensions remains a hard problem, despite advances in theory and algorithms. Multiple steps are usually required to draw unbiased samples, for example, iterations of an MCMC algorithm or integration steps in a diffusion-based amortised sampler. However,...
This framework, Coordinated Multi-Agent Diffusion Steering (CMDS), treats frozen pretrained diffusion models as reusable generative primitives and coordinates their reverse processes through a learned control, forming coordination as a stochastic optimal control problem.
ERRLESS (Entropy-Regularized Reinforcement Learning for Expression Structure Sampling), a scalable approach for sampling from the posterior distribution over expressions given data using maximum-entropy reinforcement learning, is proposed and achieves competitive results on the Feynman benchmark.
KV-streams is proposed, a plug-and-play strategy compatible with any compaction strategy that substantially increases throughput while showing no evidence of hindering performance, and is shown to be an efficient and lightweight plug-and-play addition to any post-training pipeline.
This work investigates strategic diversity, or substantive variation among approaches to a problem, as an alternative principle for constructing self-training data with two sampling methods: GROOT, a new method which constructs a hierarchical tree of approaches and samples distinct paths, and Verbalized Sampling, adapt...
It is demonstrated that the Markovian assumption can both hamper signal propagation during training and catastrophically reduce the learned sampler's expressivity due to state aliasing.
This work proposes Large Language Gibbs, a scheme for structured probabilistic inference that uses conditional distributions of an LLM as transition operators, and iteratively resample individual variables conditioned on others using an LLM's next-token conditionals to produce a stationary distribution.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
