~ similar to 2606.18186· 20 results
Renhao Zhang, Haotian Fu, Mingxi Jia, George Konidaris +2 more
The Parameterized Diffusion Policy (PDP) framework transforms diffusion models from general stochastic generators into precise, steerable tools for learning and adapting complex robotic behaviors by e…
The paper develops a quantitative framework to analyze and improve flow distillation in diffusion models, providing stability guarantees and suggesting non-uniform time scheduling to reduce approximat…
This paper shows that small forward-marginal error in score matching does not guarantee numerical stability, and constructs a smooth score field with small forward-marginal error but diverging moments…
This paper introduces a stochastic differential equation approximation for linear Temporal Difference (TD) learning under Markovian noise, explaining the constant-stepsize error floor.
Adam Wei, Nicholas Pfaff, Thomas Cohn, Arif Kerem Dayı +3 more
The paper proposes a method for imitation learning from suboptimal data in robotics.
Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo +1 more
This paper introduces MeanFlowNFT, a method that applies reinforcement learning to MeanFlow generators to improve performance and consistency.
This paper investigates the effect of pseudorandom number generator orbits on diffusion models' training and generation, revealing learnable input and significant impact on loss and quality.
This paper establishes a connection between neural network approximation of score functions and approximation of probability distributions generated by reverse diffusion models.
The paper proposes a robust training surrogate for diffusion models by replacing the standard MSE denoising loss with a nonlinear transformation induced by an f-divergence.
This paper proposes two strategies to improve feedback efficiency of reinforcement learning from human feedback (RLHF) in diffusion models.
Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu +4 more
This paper introduces Positive--Direction Matching (PDM), a branch-aware on-policy distillation objective to address Negative Branch Asymmetry (NBA) in diffusion models under classifier-free guidance.
DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…
The paper proves that diffusion models adapt to low-dimensional structure robustly across various update coefficient choices.
AdaKoop introduces an efficient streaming algorithm that models complex nonlinear dynamics from nonstationary data streams by leveraging the Koopman operator theory, achieving state-of-the-art accurac…
The authors propose a framework called Jeffrey guidance to extend diffusion-model control to target distributions beyond simple cases.