Self-Supervised Learning

Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning CVPR 2025 Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data ACL 2025 PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds CVPR 2025 Pseudo-label Data Construction Method and Syntax-enhanced Model for Chinese Semantic Error Recognition COLING 2025 PULSE: Physiological Understanding with Liquid Signal Extraction WACV 2025 Punctuation Restoration Improves Structure Understanding without Supervision NAACL 2025 Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot Transfer ICLR 2025 PVChat: Personalized Video Chat with One-Shot Learning ICCV 2025 QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation IJCAI 2025 QDTSynth: Quality-Driven Formal Theorem Synthesis for Enhancing Proving Performance of LLMs ACL 2025 Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression CVPR 2025 QuASAR: A Question-Driven Structure-Aware Approach for Table-to-Text Generation ACL 2025 Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model ICLR 2025 R²-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation IJCNLP 2025 R2-MultiOmnia: Leading Multilingual Multimodal Reasoning via Self-Training ACL 2025 RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection CVPR 2025 RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression ICLR 2025 Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image Denoising ICLR 2025 Rank-Awareness and Angular Constraints: A New Perspective on Learning Sentence Embeddings from NLI Data EMNLP 2025 RANKCLIP: Ranking-Consistent Language-Image Pretraining ICCV 2025 RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts ACL 2025 RareSyn: Health Record Synthesis for Rare Disease Diagnosis EMNLP 2025 Rationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment ACL 2025 RATIONALYST: Pre-training Process-Supervision for Improving Reasoning ACL 2025 RayZer: A Self-supervised Large View Synthesis Model ICCV 2025