arXiv Machine Learning July 20, 2026 By Hui Wei, Seyedata Jodeiri Seyedian, Xiaobai Li, Guoying Zhao

CanonicalPhys: Pose-Robust Remote Photoplethysmography via Canonical-Space Priors

Read the original on arXiv Machine Learning →

arXiv:2607. 15995v1 Announce Type: cross Abstract: Deep remote photoplethysmography (rPPG) attains sub-bpm heart-rate error on frontal, stationary faces yet degrades sharply under head pose: on MMPD, the state-of-the-art FactorizePhys backbone's MAE grows $1.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 24

Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping

arXiv:2607. 21434v1 Announce Type: cross Abstract: Video face swapping has no natural paired supervision: no real footage exists of one person's face performing another person's video.

By Logan Robbins

llms diffusion benchmarks

arXiv Machine Learning

Aug 4

Posterior Variance Is a Constraint Map, Not an Error Map: Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT

arXiv:2607. 13682v2 Announce Type: cross Abstract: Radiative Gaussian splatting reconstructs sparse-view CT fast and accurately, and recent work attaches per-Gaussian posteriors to yield per-voxel uncertainty maps.

By Chulin Zhao, Yiran Xu, Shu Liu

benchmarks safety

arXiv AI

Jun 15

Explaining RhythmFormer: A Systematic XAI Analysis of Periodic Sparse Attention for Remote Photoplethysmography

arXiv:2606. 13839v1 Announce Type: cross Abstract: Remote photoplethysmography (rPPG) transformers achieve low heart-rate error on benchmarks, yet their decisions remain opaque--a growing concern as rPPG moves toward clinical heart rate estimation.

By Louis Chen, Torbj\"orn E. M. Nordling

llms benchmarks safety

arXiv AI

Jun 4

Revisiting Model Stitching In the Foundation Model Era

arXiv:2603. 12433v3 Announce Type: replace-cross Abstract: Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility.

By Zheda Mai, Ke Zhang, Fu-En Wang, Zixiao Ken Wang, Albert Y. C. Chen, Lu Xia, Min Sun, Wei-Lun Chao, Cheng-Hao Kuo

llms multimodal

arXiv AI

Jul 7

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

arXiv:2508. 04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images.

By Rit Gangopadhyay, Jung-Hee Kim, Xien Chen, Patrick Rim, Hyoungseob Park, Alex Wong

rag diffusion fine-tuning benchmarks safety

arXiv Machine Learning

Jun 18

A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)

arXiv:2606. 18451v1 Announce Type: new Abstract: Single-image-to-3D generators are improving quickly, but there is no agreed, human-free way to tell whether one generated mesh is better than another.

By Ali Asaria, Tony Salomone, Deep Gandhi

multimodal safety

Related stories

Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping

Posterior Variance Is a Constraint Map, Not an Error Map: Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT

Explaining RhythmFormer: A Systematic XAI Analysis of Periodic Sparse Attention for Remote Photoplethysmography

Revisiting Model Stitching In the Foundation Model Era

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)