Pavlo Melnyk
  • Home
  • CV
  • Publications
  • PhD Thesis
  • News
  • Publications
    • Benchmark Dataset for Catalysis on 2D MXenes
    • Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
    • E$(n)$-Equivariant Spherical Decision Surfaces
    • QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
    • On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting
    • Equivariant Modelling for Catalysis on 2D MXenes
    • Spherical NeurO($n$)s for Geometric Deep Learning
    • O$n$ Learning Deep O$(n)$-Equivariant Hyperspheres
    • TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
    • Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
    • Steerable 3D Spherical Neurons
    • Embed Me If You Can: A Geometric Perceptron
    • A High-Performance CNN Method for Offline Handwritten Chinese Character Recognition and Visualization
  • News
    • Paper accepted at TMLR
    • Paper accepted at GRaM @ ICLR'26 (PMLR track)
    • Paper accepted at ICLR'26
    • WASP 10-Year Anniversary Feature
    • PhD Graduation Ceremony
    • PhD Defence
  • CV
  • PhD Thesis
  • Projects
  • Publications

Paper accepted at TMLR

May 25, 2026·
Pavlo Melnyk
Pavlo Melnyk
· 1 min read

FMPose teaser

“Flow Matching for Probabilistic Monocular 3D Human Pose Estimation” by Cuong Le, Pavlo Melnyk, Bastian Wandt, and Mårten Wadenbäck has been published in Transactions on Machine Learning Research!

Last updated on May 30, 2026
Academic
Pavlo Melnyk
Authors
Pavlo Melnyk
Postdoctoral Researcher
Paper accepted at GRaM @ ICLR'26 (PMLR track) Mar 2, 2026 →

© 2024-present Pavlo Melnyk. Content is licensed under CC BY-NC-ND 4.0.

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.