self-supervised learning
A form of unsupervised learning where the model generates supervisory signals from the data itself, allowing it to learn representations without the need for labeled datasets.
- 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
- 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
- Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
- Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
- Attribution-Driven Adaptive Token Pruning for Transformers
- CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
- Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
- Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning
- Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
- D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
- DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
- DINO-Foresight: Looking into the Future with DINO
- Dataset Distillation for Pre-Trained Self-Supervised Vision Models
- DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction
- Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
- Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
- Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
- Enhancing Contrastive Learning with Variable Similarity
- Enhancing Tactile-based Reinforcement Learning for Robotic Control
- Exploring Structural Degradation in Dense Representations for Self-supervised Learning
- FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
- FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
- From Faults to Features: Pretraining to Learn Robust Representations against Sensor Failures
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy
- From Synapses to Dynamics: Obtaining Function from Structure in a Connectome Constrained Model of the Head Direction Circuit
- GLNCD: Graph-Level Novel Category Discovery
- Geometric Algorithms for Neural Combinatorial Optimization with Constraints
- How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning
- HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
- Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
- InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model
- Is Limited Participant Diversity Impeding EEG-based Machine Learning?
- Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning
- Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
- MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
- Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
- Mitigating Spurious Features in Contrastive Learning with Spectral Regularization
- Neurons as Detectors of Coherent Sets in Sensory Dynamics
- Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization
- Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training
- Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
- Reinforced Context Order Recovery for Adaptive Reasoning and Planning
- Resounding Acoustic Fields with Reciprocity
- RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
- SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
- Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential
- Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
- Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models
- Self-Supervised Learning of Graph Representations for Network Intrusion Detection
- Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
- Self-supervised Blending Structural Context of Visual Molecules for Robust Drug Interaction Prediction
- Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
- Stochastic Gradients under Nuisances
- T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning
- Taming generative video models for zero-shot optical flow extraction
- Token Bottleneck: One Token to Remember Dynamics
- Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies
- Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
- Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
- UniViT: Unifying Image and Video Understanding in One Vision Encoder
- VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
- VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
- Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models
- ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
- seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models