NeurIPS 2024PastTheory
NeurIPS 2024 Workshop: Self-Supervised Learning - Theory and Practice
NeurIPS 2024 Workshop SSL
- Submission deadline
- Sep 20, 2024, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (59)
Fetched from OpenReview (v2) on 2026-06-10.
$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
A Graph Matching Approach to Balanced Data Sub-Sampling for Self-Supervised Learning
A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Adaptive Neighborhoods in Contrastive Regression Learning for Brain Age Prediction
An Empirical Analysis of Speech Self-Supervised Learning at Multiple Resolutions
Anomaly Detection In The Wild: Can SSL Handle Strong Distribution Imbalances?
Benchmarking Self-Supervised Learning for Single-Cell Data
Boosting Unsupervised Segmentation Learning
Context-Aware Predictive Coding: A Representation Learning Framework for WiFi Sensing
Data Augmentation Transformations for Self-Supervised Learning with Ultrasound
Decoupling Vertical Federated Learning using Local Self-Supervision
DIETing: Self-Supervised Learning with Instance Discrimination Learns Identifiable Features
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
EmbedSimScore: Advancing Protein Similarity Analysis with Structural and Contextual Embeddings
Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
Equivariant Representation Learning for Augmentation-based Self-Supervised Learning via Image Reconstruction
Explainable Audio-Visual Representation Learning via Prototypical Contrastive Masked Autoencoder
For Perception Tasks: The Cost of LLM Pretraining by Next-Token Prediction Outweigh its Benefits
Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles
In-Context Symmetries: Self-Supervised Learning through Contextual World Models
Influence Estimation in Self-Supervised Learning
Informed Augmentation Selection Improves Tabular Contrastive Learning
Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound
Leveraging Audio and Visual Recurrence for Unsupervised Video Highlight Detection
LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation
Masked Self-Supervised Pretraining for Semantic Segmentation of Dental Radiographs
Maven: A Multimodal Foundation Model for Supernova Science
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
NARAIM: Native Aspect Ratio Autoregressive Image Models
Neural Embeddings Rank: Aligning 3D latent dynamics with movements
Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning
On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models
PabLO: Improving Semi-Supervised Learning with Pseudolabeling Optimization
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling
Representing Positional Information in Generative World Models for Object Manipulation
Rethinking Patch Dependence for Masked Autoencoders
Robust Self-Supervised Learning for Adversarial Attack Detection
Self Supervised Learning Using Controlled Diffusion Image Augmentation
Self-Supervised Bisimulation Action Chunk Representation for Efficient RL
Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series
Self-Supervised Pretext Tasks for Event Sequence Data from Detecting Misalignment
Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
Seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
SigCLR: Sigmoid Contrastive Learning of Visual Representations
Squeezing performance from pathology foundation models with chained hyperparameter searches
Squeezing Water from a Stone: Improving Pre-Trained Self-Supervised Embeddings Through Effective Entropy Maximization
Test-Time Adaptation for Video Highlight Detection
The Birth of Self Supervised Learning: A Supervised Theory
Time-varying Representations of Longitudinal Biosignals using Self-supervised Learning
TSA on AutoPilot: Self-tuning Self-supervised Time Series Anomaly Detection
Two Is Better Than One: Aligned Clusters Improve Anomaly Detection
Uncovering RL Integration in SSL Loss: Objective-Specific Implications for Data-Efficient RL
Uncovering the Risk of Model Collapsing in Self-Supervised Continual Test-time Adaptation
Unfolding Videos Dynamics via Taylor Expansion
Unsupervised Event Outlier Detection in Continuous Time
Variational Graph Contrastive Learning
When Do We Not Need Larger Vision Models?