Continuous-time generative models, from diffusion models, flow matching, and now flow maps, owe their practical value to high-fidelity generation and steerability. In many applications, a ground-truth latent ``oracle''reward $R^*$ is unavailable or expensive to evaluate, e.g., human judgments or experimental measuremen...
Alec Sargood, Olivia Gallup, Georg Maierhofer et al.· 0 citations
Scalable approaches to learning neural dynamical systems have placed diffusion, flow matching, and few-step generators in flow maps at the forefront of generative modeling. Such state-of-the-art models have limited access to explicit model densities despite evolving from classical generative modeling approaches that le...
Francesco Ruscio, Timothy James Hitge, Fred Zhangzhi Peng et al.· 0 citations
This paper introduces Kinematic Interpolants (KI), a novel framework that extends the seminal methodology of stochastic interpolants to infer nonlinear dynamics across multiple snapshots in phase space, i.e., observables with position and velocity measurements.
Yi-Heng Jiang, Youssef M. Marzouk, A. Bose et al.· 0 citations
Relay introduces a differentiable per-token channel that passes information between forward passes and is trained via truncated backpropagation through time (BPTT), demonstrating that state-of-the-art DLMs can be explicitly trained to relay latent information forward across decoding steps, advancing the performance-lat...
Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
