The paper introduces Difficulty-Calibrated Flow Matching, a method that adapts the noise-to-data interpolation schedule in Conditional Flow Matching based on a pilot run’s loss profile. By setting the schedule to the quantile function of this difficulty profile, the training trajectory spends more time where the velocity is hardest to learn. Experiments on CIFAR-10, MNIST, and Fashion‑MNIST show that this calibrated path achieves the best FID on CIFAR‑10 and outperforms all fixed schedules in large‑batch, few‑update settings, where compute is most limited.
By Airin Akter Tania, Md Raihan Khan
RiskTraf introduces a risk-extrapolated residual learning approach for multi-variate traffic flow prediction, leveraging raw flow, speed, and occupancy data from the new PEMSB-3V benchmark. The method freezes a trained spatio-temporal backbone and adds a lightweight residual head that learns from historical speed and occupancy to correct flow predictions across different traffic regimes. Experiments show consistent improvements over various backbones and outperform existing debiasing and distribution-shift adaptation techniques.
By Guangyu Wang, Zhidan Liu
arXiv:2605. 27991v2 Announce Type: replace-cross Abstract: Gradient-flow optimization is usually viewed as an algorithmic procedure for minimizing empirical loss, with training duration selected by validation or heuristic early-stopping rules.
By Minhao Yao, Ruoyu Wang, Xihong Lin, Lin Liu, Zhonghua Liu
Policy‑Mask is a budget‑aware policy that jointly selects a timestep, a diffusion block, and a subset of channels from a frozen diffusion model to optimize downstream discriminative tasks. By normalizing channel scores and training on the downstream objective, it outperforms fixed‑extraction baselines on segmentation, classification, and semantic correspondence, achieving state‑of‑the‑art results on ADE20K, CIFAR‑100, and SPair‑71k. The method also extends to diffusion transformers by mapping U‑Net channels to image‑token hidden dimensions.
By Ivan Listopadov, Maksim Nakhodnov, Aibek Alanov
Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^ωq_0^{1-ω}$. We analyze CFG through the probability flow ODE and derive exact analytic path-integral representations of the induced distributions for both constant and time-dependent guidance.
arXiv:2610.03503v1 Announce Type: new
Abstract: Training-free posterior sampling methods, also known as Plug-and-Play methods, leverage pretrained unconditional diffusion or flow-matching models to s...
By Liam Moroy, Jean-Fran\c{c}ois Giovannelli, Yoann Altmann, Steve McLaughlin, Fr\'ed\'eric Champagnat, Guillaume Bourmaud
The study evaluates self‑supervised pretraining for Prognostics and Health Management (PHM) across 47 public datasets, using a compact Transformer encoder trained with masked patch prediction. Transfer performance is highly task‑dependent: it dramatically improves fault‑classification on CWRU and HSG18 but offers no reliable benefit for remaining‑useful‑life estimation on CMAPSS. The authors also compare centralized versus simulated federated pretraining, finding that centralized training generally outperforms federated training under matched budgets, and that the intrinsic SSL loss does not reliably predict downstream performance.
By Jos\'e Sanz-Dur\'an, David Sol\'is-Mart\'in
arXiv:2607. 19725v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^\omega q_0^{1-\omega}$.
By Enze Jiang, Zheng Ma
Preconditioned Flow Matching introduces a precondition-then-match framework that transforms target distributions into more isotropic representations before training flow matching models. By reshaping intermediate distributions, the method improves conditioning, leading to better low-eigenvalue recovery and enhanced performance metrics such as FID, MMD, precision, and recall across Gaussian, Gaussian-mixture, and high-resolution image datasets. The approach is theoretically justified and empirically validated, with ablations showing gains stem from improved geometry rather than extra parameters.
By Shadab Ahamed, Eshed Gal, Md Shahriar Rahim Siddiqui, Simon Ghyselincks, Moshe Eliasof, Eldad Haber
The paper introduces TRACK, a training‑free trajectory routing method that accelerates video diffusion by selectively switching between large and small models during denoising steps. A calibration process generates a disagreement score map, guiding the selection of the appropriate model at each step to maintain quality while reducing computational cost. Experiments on Wan 2.1, Cosmos 3, TurboDiffusion, and FastVideo show speedups ranging from 1.95× to 2.73× with comparable quality and diversity.
By Mustafa Munir, Huy Vu, Shreyas Misra, Rohit Jena, Sajad Norouzi, Ali Taghibakhshi, Anis Ahmad, Anjul Patney, Pavlo Molchanov, Nima Tajbakhsh
Modern deep networks are trained through long update trajectories, yet their temporal organization remains less systematically characterized than architectures, losses, or optimizers. We study short-h...
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.