Set Transformer

Latest papers

8 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Learning Incompressible 3D Flows from Sparse Samples: A Set Transformer Approach to Divergence-Free Kernel Fitting
Oct 12, 2026Ramzi Idoughi, Radouan Boukharfane, Peter WonkaSet Transformer Computational Fluid Dynamics
King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Mohammed VI Polytechnic University (UM6P), Benguerir, Morocco
Association profile conditioning in a set-temporal transformer for cross-session intracortical motor decoding
Sep 30, 2026Xinyuan Zhang, Handong Mo, Pengfei Wen +5Set Transformer Transformer
The University of Hong Kong, Hong Kong SAR, China · Southern University of Science and Technology, Shenzhen, China
LENS-GRF: Permutation-Invariant Lesion Evidence Network with Gated Residual Fusion for Acne Severity Grading and Multi-Rater Clinical Oracle Analysis
Sep 25, 2026Muhammad Muhtasim Shahriar, M. F. MridhaSet Transformer Automated Grading
Department of Computer Science, International Islamic University Chittagong (IIUC), Chittagong, Bangladesh · Department of Computer Science, American International University-Bangladesh (AIUB), Dhaka, Bangladesh
Matilda: Engine-Agnostic Search with Human Policy Guidance
Jun 23, 2026Jason CarlsonSet Transformer Game-Playing Agents
Set-Based Transformer for Atmospheric Compensation in Standoff LWIR Hyperspectral Imaging
Jun 6, 2026Fabian Perez, Nicolas Quintero, Jeferson Acevedo +1Thermal Imaging Set Transformer
Department of Computer Science, Universidad Industrial de Santander
Attention-based optimizer for symmetry finding
May 28, 2026Shreya Banerjee, Vinodh Raj Rajagopal Muthu, Charlie Nation +5Set Transformer Quantum Many-Body Physics
Department of Physics and Astronomy, University of Exeter, Stocker Road, Exeter EX4 4QL, United Kingdom · Institute for Quantum Computing, University of Waterloo, Waterloo, ON N2L 3G1, Canada · QuAOS collaboration
Hypernetworks for Dynamic Feature Selection
May 12, 2026Javier Fumanal-Idocin, Raquel Fernandez-Peralta, Javier Andreu-PerezSet Transformer Hypernetworks
University of Essex Wivenhoe Park, Colchester, United Kingdom · Slovak Academy of Sciences Štefánikova 49, 814 73 Bratislava, Slovakia
Structure-Aware Set Transformers: Temporal and Variable-Type Attention Biases for Asynchronous Clinical Time Series
Feb 18, 2026Joohyung Lee, Kwanhyung Lee, Changhun Kim +1Set Transformer Irregular Time-Series Modeling
AITRICS · Korea Advanced Institute of Science and Technology (KAIST)

Oct 12, 2026J/K move · Enter open · S save

Learning Incompressible 3D Flows from Sparse Samples: A Set Transformer Approach to Divergence-Free Kernel Fitting

Ramzi Idoughi, Radouan Boukharfane, Peter Wonka

King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Mohammed VI Polytechnic University (UM6P), Benguerir, Morocco

Set Transformer Computational Fluid Dynamics Sparse Recovery Kernel Methods Transformer

Open paper AskPDF arXiv

Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations, and robustness to missing data. We introduce DFK-Former, a set-to-field transformer that reconstructs divergence-free velocity fields from sparse, noisy, and irregularly sampled 3D observations. The model is inherently invariant to the number and ordering of input samples and predicts the parameters of a divergence-free kernel representation, producing continuous, mesh-free velocity fields that satisfy incompressibility exactly by construction rather than approximately through soft constraints or projection operators. Unlike existing divergence-free kernel approaches, which estimate kernel coefficients via a separate optimization for each field, DFK-Former predicts these coefficients directly in a single forward pass. This eliminates costly iterative fitting while providing a learned prior that enables accurate reconstruction even when observations are insufficient to uniquely determine the field. To enhance representational power, we introduce adaptive and anisotropic divergence-free kernels that preserve exact incompressibility guarantees while capturing more complex flow structures. Extensive experiments across varying levels of sparsity, noise, and occlusion, including transfer to real Direct Numerical Simulation (DNS) turbulence data, demonstrate substantial gains in both accuracy and efficiency. DFK-Former reduces endpoint error by up to 4.6x compared to per-field divergence-free-kernel optimization, while reconstructing each field in 7.5 ms instead of 9.8 s, yielding a speedup of more than three orders of magnitude. These results establish direct, feed-forward prediction of divergence-free kernel parameters as a practical and effective paradigm for physically consistent velocity-field reconstruction from sparse observations.