Set Transformer
PulseAugur coverage of Set Transformer — every cluster mentioning Set Transformer across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
STAR-XPC model estimates X-ray transmission in milliseconds
Researchers have developed STAR-XPC, a Set Transformer model designed to estimate X-ray transmission in polymer composites. This model significantly accelerates the process compared to traditional Monte Carlo simulation…
-
New Transformer Model Reconstructs 3D Flows from Sparse Data
Researchers have developed DFK-Former, a novel set-to-field transformer model capable of reconstructing incompressible 3D velocity fields from sparse and noisy data. This model predicts the parameters of a divergence-fr…
-
AI frameworks developed for acne severity grading and analysis
Researchers have developed two new frameworks, LENS-GRF and CG-HAF, for grading acne severity using AI. LENS-GRF, a permutation-invariant network, combines global facial context with detailed lesion analysis, achieving …
-
LLM-generated recipe data validated by new soundness assessment workflow
Researchers have developed a semi-automated workflow to assess the soundness of recipe data generated or augmented by Large Language Models (LLMs). This method, applied to a knowledge graph of Indian food, identifies an…
-
Graph Transformers for MILPs Limited by 1-WL Test, Study Finds
A new paper characterizes the expressive power of global-attention graph transformers used for mixed-integer linear programs (MILPs). The research proves that these models, including architectures like Graphormer and Se…
-
Deep-learning tool rapidly assesses post-hurricane grid damage and schedules repairs
Researchers have developed a two-stage deep-learning tool to expedite post-hurricane damage assessment and repair scheduling for electrical grids. The first stage identifies damaged lines using models like MLP, ResMLP, …
-
New MMD-Reg method offers scalable, differentiable point-cloud registration
Researchers have introduced MMD-Reg, a new method for point-cloud registration that is both differentiable and computationally efficient. This approach models registration as a nonlinear least-squares problem using Maxi…
-
AI framework identifies physical symmetries using attention mechanisms
Researchers have developed a novel optimization framework that leverages a Set-Transformer architecture with self-attention mechanisms to identify symmetries in physical models. This machine learning-based approach enco…
-
New SAVER framework selectively uses visual evidence for multimodal extraction
Researchers have developed SAVER, a novel framework designed to improve multimodal information extraction from social media posts. This system selectively utilizes visual evidence from attached images, rather than proce…