Self-Supervised Learning

Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification RSS 2025 Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting AAAI 2025 Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning IJCNLP 2025 Understanding the Influence of Synthetic Data for Text Embedders ACL 2025 Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning EMNLP 2025 Unfamiliar Finetuning Examples Control How Language Models Hallucinate NAACL 2025 Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision AAAI 2025 Unified Multi-Agent Trajectory Modeling with Masked Trajectory Diffusion ICCV 2025 UniFORM: Towards Unified Framework for Anomaly Detection on Graphs AAAI 2025 Unifying Causal Representation Learning with the Invariance Principle ICLR 2025 UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers NAACL 2025 UniMath-CoT: A Unified Framework for Multimodal Mathematical Reasoning with Re-Inference Affirmation EMNLP 2025 UniTMGE: Uniform Text-Motion Generation and Editing Model via Diffusion WACV 2025 Universal Graph Self-Contrastive Learning IJCAI 2025 Universal Image Restoration Pre-training via Degradation Classification ICLR 2025 Universal Scene Graph Generation CVPR 2025 Unlearning the Noisy Correspondence Makes CLIP More Robust ICCV 2025 Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation CVPR 2025 Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch ACL 2025 Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation CVPR 2025 Unleashing the Reasoning Potential of LLMs by Critique Fine-Tuning on One Problem EMNLP 2025 Unseen Visual Anomaly Generation CVPR 2025 Unsupervised Discovery of Facial Landmarks and Head Pose CVPR 2025 Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming IJCAI 2025 Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning CVPR 2025