arXiv Machine Learning
Learned Adaptive Multiresolution Diffusion Imaging
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 4
When Do Surrogate Updates Improve Decisions? A Local Theory of Trajectory-Wise Transfer
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
arXiv Computer Vision
Nov 2
Scout-Refine-Correct: Teaching Flow Models to Refine Their Own Samples
Scout-Refine-Correct (SRC) is a training recipe that equips flow-matching image generation models with an inference-time refinement capability. During sampling, the model performs a scout rollout to predict a full sample, uses this prediction as a self-conditioning signal, and then takes the actual step; this process can be repeated for multiple refinement rounds. On ImageNet-256, SRC improves LightningDiT-B’s FID from ~14.5 to ~7.26 with 550 normalised flow evaluations, matching a best-of‑N baseline that relies on an oracle verifier, and further reduces FID to 3.81 when combined with best-of‑N.
arXiv AI
Sep 24
Learning Spectral Allocation: A Fractional Diffusion Framework for Adaptive Volumetric Segmentation
The paper introduces FHEAT, a fractional diffusion operator derived from the discrete cosine transform, to learn how much spectral mixing each stage of a 3D medical segmentation network should perform. By reparameterizing the operator with a semigroup time, the authors enable the optimizer to decide whether global mixing is needed, resulting in a lightweight U‑shaped architecture (Light‑UNETR) paired with a Kolmogorov‑Arnold mixer (KAN3D). In semi‑supervised experiments, FHEAT‑Seg achieves state‑of‑the‑art Dice scores while dramatically reducing FLOPs through learned spectral sparsification.
arXiv AI
Oct 2
Useful to Whom? Sample Value Is Defined Only Relative to the Learner
The paper investigates how the usefulness of training samples, as determined by coreset selection, depends on the learner rather than just the data. Experiments on ImageNet-100 and ImageNet-1k show that changing model width, input grid, stride, and architecture (e.g., ResNet vs. ViT) shifts the crossover point where different selection criteria (easy-first vs. geometric coverage) become optimal. These findings demonstrate that the relative value of a fixed subset of samples varies with the target learner’s capacity and structure, and that selection strategies must be tuned to the specific model they will train.
arXiv AI
Oct 21
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
arXiv:2609.35767v2 Announce Type: replace-cross Abstract: Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image g...
arXiv Machine Learning
Sep 30
The Decision Value of Perception Compute
arXiv:2609.35910v1 Announce Type: new Abstract: Adaptive perception spends extra computation on inputs where perception is expected to improve. When perception feeds a downstream decision system, a b...