Artificial Intelligence

Curating Demonstrations using Online Experience RSS 2025 CURE: Controlled Unlearning for Robust Embeddings — Mitigating Conceptual Shortcuts in Pre-Trained Language Models EMNLP 2025 CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems ICCV 2025 CureGraph: Contrastive Multi-Modal Graph Representation Learning for Urban Living Circle Health Profiling and Prediction (Abstract Reprint) IJCAI 2025 CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning ICLR 2025 Curiosity-Driven Reinforcement Learning from Human Feedback ACL 2025 CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning NAACL 2025 Curriculum Abductive Learning for Mitigating Reasoning Shortcuts IJCAI 2025 Curriculum Conditioned Diffusion for Multimodal Recommendation AAAI 2025 Curriculum Direct Preference Optimization for Diffusion and Consistency Models CVPR 2025 Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning EMNLP 2025 Curse of bilinguality: Evaluating monolingual and bilingual language models on Chinese linguistic benchmarks ACL 2025 Curse of High Dimensionality Issue in Transformer for Long Context Modeling ICML 2025 Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation EMNLP 2025 CursorCore: Assist Programming through Aligning Anything ICML 2025 CustAny: Customizing Anything from A Single Example CVPR 2025 CustomContrast: A Multilevel Contrastive Perspective for Subject-Driven Text-to-Image Customization AAAI 2025 CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities AAAI 2025 Customized Condition Controllable Generation for Video Soundtrack CVPR 2025 CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation CVPR 2025 CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages COLING 2025 Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning ICML 2025 Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems ICLR 2025 Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025 CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities ICML 2025