self-supervised learning

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation ICCV 2025 Tone recognition in low-resource languages of North-East India: peeling the layers of SSL-based speech models Interspeech 2025 Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion Interspeech 2025 Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction AAAI 2025 Towards Classification of Typical and Atypical Disfluencies: A Self Supervised Representation Approach Interspeech 2025 Towards Early Prediction of Self-Supervised Speech Model Performance Interspeech 2025 Towards Efficient General Feature Prediction in Masked Skeleton Modeling ICCV 2025 Towards More Discriminative Feature Learning in SNNs with Temporal-Self-Erasing Supervision AAAI 2025 Towards Robust Deterministic and Probabilistic Modeling for Predictive Learning IJCAI 2025 Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM Interspeech 2025 Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression ICLR 2025 Towards Ship License Plate Recognition in the Wild: A Large Benchmark and Strong Baseline AAAI 2025 TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos ICCV 2025 Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection ICCV 2025 TrackVerse: A Large-Scale Object-Centric Video Dataset for Image-Level Representation Learning ICCV 2025 Training Articulatory Inversion Models for Interspeaker Consistency Interspeech 2025 Transformer-based Speech Model Learns Well as Infants and Encodes Abstractions through Exemplars in the Poverty of the Stimulus Environment COLING 2025 Transparent and Coherent Procedural Mistake Detection EMNLP 2025 Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks ACL 2025 TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning AAAI 2025 Tuned Contrastive Learning WACV 2025 Type Information-Assisted Self-Supervised Knowledge Graph Denoising AISTATS 2025 UCM-VeID V2: A Richer Dataset and A Pre-training Method for UAV Cross-Modality Vehicle Re-Identification CVPR 2025 UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint ICCV 2025 Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology WACV 2025