SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
Gross, Francisco Massa, A
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
SMR uses multi-channel map-encoded reinforcement learning to achieve roughly 10% better time utilization than greedy baselines for single-dish radio telescope scheduling.
Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.
ClusterRAG applies density-based clustering to user profiles for collaborative retrieval in personalized RAG and reports best performance on LaMP tasks by combining target and similar-user profiles.
SparseBalance dynamically adjusts sparsity and batches workloads to load-balance sparse attention training, delivering up to 1.33x speedup and 0.46% better long-context performance on LongBench.
Emulator-based component analysis decomposes structural sources of variance in simulated UV-vis spectra of ethanolic trans-azobenzene and flags overrepresented geometries after wavelength-specific photoexcitation.
citing papers explorer
-
Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
-
SMR: Scheduler with Multi-Channel Map-Encoded Reinforcement Learning for Radio Telescopes
SMR uses multi-channel map-encoded reinforcement learning to achieve roughly 10% better time utilization than greedy baselines for single-dish radio telescope scheduling.
-
Controlling Transient Amplification Improves Long-horizon Rollouts
Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.
-
ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
ClusterRAG applies density-based clustering to user profiles for collaborative retrieval in personalized RAG and reports best performance on LaMP tasks by combining target and similar-user profiles.
-
SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention
SparseBalance dynamically adjusts sparsity and batches workloads to load-balance sparse attention training, delivering up to 1.33x speedup and 0.46% better long-context performance on LongBench.
-
Structural Decomposition of UV--Visible Spectral Variation: Azobenzene in Ethanol Solution
Emulator-based component analysis decomposes structural sources of variance in simulated UV-vis spectra of ethanolic trans-azobenzene and flags overrepresented geometries after wavelength-specific photoexcitation.
- DELOS: Contrastive Deep Learning for Low-SNR Blind Transit Searches in Kepler Photometry
- The EDGE Language: Extended General Einsums for Graph Algorithms