Self-Supervised Learning

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning ICLR 2025 Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning AAAI 2025 From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions NAACL 2025 From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration CVPR 2025 From Imitation to Introspection: Probing Self-Consciousness in Language Models ACL 2025 From Implicit Exploration to Structured Reasoning: Guideline and Refinement for LLMs EMNLP 2025 From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations ICCV 2025 From Noise to Clarity: Filtering Real and LLM-Generated Samples for Enhanced Intent Detection EMNLP 2025 From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model EMNLP 2025 From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling CVPR 2025 From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding ACL 2025 From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs ICML 2025 From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining ICML 2025 FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors CVPR 2025 FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning CVPR 2025 Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning ACL 2025 FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data WACV 2025 G2PDiffusion: Cross-Species Genotype-to-Phenotype Prediction via Evolutionary Diffusion ICCV 2025 Galileo: Learning Global & Local Features of Many Remote Sensing Modalities ICML 2025 GAMIC: Graph-Aligned Molecular In-context Learning for Molecule Analysis via LLMs EMNLP 2025 Gaussian-based World Model: Gaussian Priors for Voxel-Based Occupancy Prediction and Future Motion Prediction ICCV 2025 GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting ICCV 2025 Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders CVPR 2025 GECO: Geometrically Consistent Embedding with Lightspeed Inference ICCV 2025 Generalist Robot Manipulation beyond Action Labeled Data CoRL 2025