Self-Supervised Learning

Diffusion-Based Generative Regularization for Supervised Discriminative Learning WACV 2025 Diffusion-based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection AAAI 2025 Diffusion Feedback Helps CLIP See Better ICLR 2025 Diffusion Model is Effectively Its Own Teacher CVPR 2025 Diffusion Models are Evolutionary Algorithms ICLR 2025 Diffusion On Syntax Trees For Program Synthesis ICLR 2025 DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment CVPR 2025 Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback ACL 2025 Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models AAAI 2025 DisCo: Discovering Common Affordance from Large Models for Actionable Part Perception WACV 2025 Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning ICML 2025 Disentangled and Personalized Representation Learning for Next Point-of-Interest Recommendation IJCAI 2025 Disentangled Modeling of Preferences and Social Influence for Group Recommendation AAAI 2025 Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning ACL 2025 Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal AAAI 2025 Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks AAAI 2025 Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts ICML 2025 Disentangling Multi-view Representations via Curriculum Learning with Learnable Prior IJCAI 2025 Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning ACL 2025 Disentangling Representations through Multi-task Learning ICLR 2025 Disentangling Subject-Irrelevant Elements in Personalized Text-to-Image Diffusion via Filtered Self-Distillation WACV 2025 Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction ICCV 2025 Distilling an End-to-End Voice Assistant Without Instruction Training Data ACL 2025 Distilling Structural Representations into Protein Sequence Models ICLR 2025 DistinctAD: Distinctive Audio Description Generation in Contexts CVPR 2025