SPAR: Placement-aware Self-Supervised Representation Learning for Distributed Sensing
cs.LG
Submitted: 2025-05-22
Updated: 2026-11-13
Terminology
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting
- TimeGPT-1
- Contrastive Audio-Visual Masked Autoencoder
- MOMENT: A Family of Open Time-series Foundation Models
- Self Pre-training with Topology- and Spatiality-aware Masked Autoencoders for 3D Medical Image Segmentation
- USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- SLM: Learning a Discourse Language Representation with Sentence Unshuffling
- Ti-MAE: Self-Supervised Masked Time Series Autoencoders
- IoT-LM: Large Multisensory Language Models for the Internet of Things
- Order-Based Pre-training Strategies for Procedural Text Understanding
- MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
- StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
- Position Prediction as an Effective Pretraining Strategy
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis