arXiv:2606. 01273v1 Announce Type: new Abstract: Spatio-temporal point processes (STPPs) provide a principled framework for modeling asynchronous events in continuous time and space.
arXiv:2507. 08390v5 Announce Type: replace Abstract: Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training.
arXiv:2608. 03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents.
The paper investigates training diffusion models to sample from distributions defined by unnormalized densities or energy functions. It benchmarks various diffusion-structured inference techniques, including simulation-based variational methods and off-policy approaches such as continuous generative flow networks, highlighting their relative strengths and challenging some prior claims. Additionally, the authors introduce a new exploration strategy for off-policy methods that employs local search in the target space with a replay buffer, demonstrating improved sample quality across multiple target distributions.
The paper introduces a divide-and-conquer neural Bayes estimation framework for spatial and spatiotemporal point process models. It uses transformer-based architectures on partitions of the domain and an attention mechanism to combine local summaries, enabling direct inference from raw point pattern data. Simulation studies show reliable inference with better scalability than existing neural and classical likelihood-based methods, and the approach is applied to whale call data in Cape Cod Bay, producing parameter estimates and credible intervals at negligible cost after training.
Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but lack visual foresight, while navigation world models can anticipate future observations but often require costly planning rollouts.
The paper introduces QuAKE, a Quantization-Aware Kalman Estimator designed to correct errors in diffusion model sampling when using quantized denoisers. By treating sampling as an online estimation problem, QuAKE leverages the history of quantized outputs to recover full-precision estimates, updating a posterior in closed form at each step. The method is lightweight, plug‑and‑play, and works with any high‑order multistep ODE sampler, outperforming existing correction techniques on W4A4‑quantized text‑to‑image diffusion models.
Diffusion models have shown strong potential for multi-modal planning in end-to-end autonomous driving. However, most existing methods confine diffusion to the planning module, conditioning on fixed outputs from separate discriminative perception networks.
arXiv:2609.00279v1 Announce Type: cross Abstract: This work shows that diffusion models learned with standard denoising loss can provide effective global MCMC proposals for complex high-dimensional t...
arXiv:2608. 14067v1 Announce Type: new Abstract: Diffusion models offer a natural way to model uncertainty in time series forecasting, yet their iterative sampling process is often treated as a uniformly beneficial refinement procedure.
Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop driving.
arXiv:2606. 14313v1 Announce Type: cross Abstract: Real-world spatio-temporal forecasting must handle irregular time points, spatially sparse observations, and the need for uncertainty quantification.
Accelerating Video Diffusion via Training-Free Trajectory Routing (TRACK) introduces a heterogeneous denoising strategy that switches between large and small diffusion models at selected steps, determined by a calibration process that measures disagreement between model predictions. By routing quality-sensitive steps to the large model and low-disagreement steps to the small model, TRACK achieves significant speedups—up to 2.73×—across several video diffusion benchmarks while maintaining comparable quality and diversity. The method requires no retraining, architectural changes, or online dual-model evaluation, making it a practical acceleration paradigm for video diffusion.