inductive bias
The set of assumptions that a learning algorithm makes to generalize from the training data to unseen data. Understanding inductive bias helps in selecting appropriate models and algorithms for specific tasks.
- 4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
- AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
- Anatomically inspired digital twins capture hierarchical object representations in visual cortex
- BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
- Block-Biased Mamba for Long-Range Sequence Processing
- Bridging Expressivity and Scalability with Adaptive Unitary SSMs
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding
- Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
- Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
- Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
- Efficient Bayesian Experiment Design with Equivariant Networks
- Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
- Is Your Diffusion Model Actually Denoising?
- Kuramoto Orientation Diffusion Models
- Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning
- Learning to cluster neuronal function
- Locality in Image Diffusion Models Emerges from Data Statistics
- Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
- MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling
- Monotone and Separable Set Functions: Characterizations and Neural Models
- Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
- PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations
- Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery
- Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
- SegMASt3R: Geometry Grounded Segment Matching
- Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
- Structured Initialization for Vision Transformers
- Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement