Machine Learning

No-Regret Bayesian Optimization with Stochastic Observation Failures AISTATS 2025 No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization ICML 2025 No Regret Reinforcement Learning Algorithms for Online Scheduling with Multi-Stage Tasks IJCAI 2025 NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models NAACL 2025 Normalize Then Propagate: Efficient Homophilous Regularization for Few-Shot Semi-Supervised Node Classification AAAI 2025 NormAL LoRA: What is the perfect size? EMNLP 2025 Norm of Mean Contextualized Embeddings Determines their Variance COLING 2025 NormXLogit: The Head-on-Top Never Lies EMNLP 2025 Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization COLING 2025 No Simple Answer to Data Complexity: An Examination of Instance-Level Complexity Metrics for Classification Tasks NAACL 2025 No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Size COLING 2025 Nota AI at GenAI Detection Task 1: Unseen Language-Aware Detection System for Multilingual Machine-Generated Text COLING 2025 NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms IJCAI 2025 Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models NAACL 2025 Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models EMNLP 2025 Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization NAACL 2025 Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning ICLR 2025 Not All Language Model Features Are One-Dimensionally Linear ICLR 2025 Not All Layers of LLMs Are Necessary During Inference IJCAI 2025 Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification ICLR 2025 Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing EMNLP 2025 Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance EMNLP 2025 Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability CVPR 2025 Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models ICLR 2025 Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks ICML 2025