QGF performs test-time policy optimization for flow models in RL by guiding a behavior-cloned reference policy with value-function gradients, achieving strong results on high-dimensional offline RL benchmarks without additional policy training.
Energy-weighted flow matching for offline reinforcement learning
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 3representative citing papers
Introduces Block-R1 benchmark, Block-R1-41K dataset, and a conflict score to handle domain-specific optimal block sizes in RL post-training of diffusion LLMs.
ScoRe-Flow achieves decoupled mean-variance control in stochastic flow matching by deriving a closed-form score for drift modulation plus learned variance, yielding faster RL convergence and higher success rates on locomotion and manipulation benchmarks.
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
Dual-Flow RL jointly models return distributions and multimodal policies via conditional flow matching with an added ECER for exploration, claiming SOTA results on control benchmarks.
GDSD reduces RL for dLLMs to likelihood-free self-distillation via a normalization-free logit-matching objective, outperforming ELBO methods with more stable training on LLaDA-8B and Dream-7B.
PCBF learns return distributions via source-consistent Bellman-coupled paths with shared noise and λ-parameterized control variates, reporting improved fidelity and stability on MRPs, OGBench, and D4RL.
FAN simplifies expressive flow policies and distributional critics in offline RL via single-iteration behavior regularization and single-sample noise conditioning to claim SOTA performance with lower training and inference time.
Fisher Decorator refines flow policies in offline RL via a local transport map and Fisher-matrix quadratic approximation of the KL constraint, yielding controllable error near the optimum and SOTA benchmark results.
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and annealed variants showing competitive performance on benchmarks.
FlowAWR derives an advantage-weighted rectification for optimal velocity fields in flow models, claiming 2-5x faster convergence than DiffusionNFT on SD3.5-Medium.
citing papers explorer
No citing papers match the current filters.