The paper introduces TDAction, a method for one‑step generative modeling that selects transport targets during training based on a cost reflecting shared‑parameter effort and terminal mismatch. By formulating this as a soft‑terminal control problem, the authors derive a closed‑form Batch Tangent Action‑to‑Go value that captures cross‑sample interactions and can be efficiently implemented with randomized tangent probes. Experiments on ImageNet 256×256 demonstrate that TDAction achieves an FID below 1.1 without distillation.
arXiv:2609.37113v1 Announce Type: new Abstract: Generalized reaction-diffusion systems encompass diverse transport mechanisms and coupled reaction kinetics. A central question for neural PDE solvers...
arXiv:2604. 18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern when compute is limited.
arXiv:2609.15883v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies...
arXiv:2607. 18198v1 Announce Type: new Abstract: Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization.
The paper argues that diffusion-based action policies can use a frozen, observation‑free backbone as a reusable trajectory prior, with task adaptation handled entirely by the conditioning pathway. By pretraining a general action head on forward‑kinematics data and then freezing it, the authors show that a single backbone can match or outperform normally trained models on MimicGen and LIBERO. Their experiments reveal that a small 5 M‑parameter MLP backbone can rival large U‑Net and transformer backbones, indicating that action backbones are often over‑parameterized and that image‑style architectures may not be the best fit for low‑dimensional action generation.
arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.
Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator.
arXiv:2606. 30376v1 Announce Type: new Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods.
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
arXiv:2608. 13096v1 Announce Type: new Abstract: Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially.
arXiv:2606. 08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map.
arXiv:2609.25444v1 Announce Type: new Abstract: This work studies prediction parameterization for stochastic generative dynamics in diffusion models. Existing velocity-based generative models provide...