SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
PulseAugur coverage of SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks — every cluster mentioning SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
CoStream framework composes simple behaviors for complex robotic manipulation
Researchers have introduced CoStream, a novel framework designed to enable complex manipulation tasks in robotics by composing simpler, independent behaviors. This approach leverages foundation models and diverse sensin…
-
Calousel method calibrates non-overlapping multi-camera systems using rotation
Researchers have developed a new method called Calousel for calibrating multi-camera systems that do not have overlapping fields of view. This approach utilizes pure rotational motion and a single static calibration boa…
-
New Riemannian MeanFlow method enables faster generative model sampling
Researchers have introduced Riemannian MeanFlow (RMF), a novel method for generative models operating on Riemannian manifolds. Unlike previous approaches that require extensive simulation for sampling, RMF enables one-s…
-
New Bayesian 3D Steerable CNNs Quantify Uncertainty
Researchers have developed a novel Bayesian 3D Steerable CNN that simultaneously achieves SE(3)-equivariance and quantifies uncertainty. This new model places posterior distributions over kernel coefficients, enabling s…
-
New AI Model Generates Dexterous Robot Grasps with Force Prediction
Researchers have developed EquiDexFlow, a novel SE(3)-equivariant flow-matching model designed to generate dexterous grasps for robotic hands. Unlike previous methods that treat contact forces as a secondary verificatio…
-
New ENBP framework respects SE(3) symmetry for faster AI inference
Researchers have developed Equivariant Neural Belief Propagation (ENBP), a new framework for probabilistic inference that respects SE(3) symmetry. ENBP utilizes equivariant Gaussian mixture models for messages, enabling…
-
Dual Quaternion Algorithm Enhances Pose Recovery in Robotics and 3D Vision
Researchers have developed a novel algorithm for SE(3) synchronization, a critical task in robotics and 3D vision for recovering absolute poses from noisy relative transformations. This new method utilizes dual quaterni…
-
New Neural Network Embeds Lie Groups for Robotics and Control
Researchers have developed a novel approach called Lie group embedded dynamical neural networks (LieEDNN) to address challenges in modeling continuous symmetries and non-Euclidean dynamics within neural networks. This m…
-
OASIS policy aligns robot action and observation spaces
Researchers have introduced OASIS, a novel visuomotor policy designed to improve robotic manipulation by aligning the observation and action spaces. This approach utilizes SE(3) end-effector trajectory prediction to ens…
-
New benchmark and self-supervised model advance protein fold classification
Researchers have developed TEDBench, a new large-scale benchmark for protein fold classification, designed to overcome limitations in existing datasets and models. To address performance issues with current methods, the…
-
Meta-LegNet framework accelerates catalyst screening with transferable adsorption environment learning
Researchers have developed Meta-LegNet, a novel graph learning framework designed to predict surface adsorption configurations in computational catalysis. This framework utilizes SE(3)-equivariant atom-level message pas…
-
New framework unifies entropic OT with neural networks on curved spaces
Researchers have introduced Entropic Riemannian Neural Optimal Transport (Entropic RNOT), a novel framework designed to handle machine learning problems involving data on curved spaces. This method unifies intrinsic ent…
-
New DenSNet model enhances molecular dynamics with machine-learned electron densities
Researchers have developed DenSNet, a novel machine-learning approach for electronic structure calculations that predicts the ground-state electron density. This method utilizes SE(3)-equivariant neural networks and a $…