Machine Learning

On the Robustness of Agentic Function Calling NAACL 2025 On the Robustness of Distributed Machine Learning Against Transfer Attacks AAAI 2025 On the Robustness of Kernel Goodness-of-Fit Tests JMLR 2025 On the Robustness of Reward Models for Language Model Alignment ICML 2025 On the Robustness Tradeoff in Fine-Tuning ICCV 2025 On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions EMNLP 2025 On the Role of Key Phrases in Argument Mining NAACL 2025 On the Role of Label Noise in the Feature Learning Process ICML 2025 On the Role of Model Prior in Real-World Inductive Reasoning EMNLP 2025 On the Role of Speech Data in Reducing Toxicity Detection Bias NAACL 2025 On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs EMNLP 2025 On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts EMNLP 2025 On the Sample Complexity of Next-Token Prediction AISTATS 2025 On the Similarities of Embeddings in Contrastive Learning ICML 2025 On the Statistical Mechanisms of Distributional Compositional Generalization ICML 2025 On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension JMLR 2025 On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning ICML 2025 On the Tolerance of Repetition Before Performance Degradation in Kiswahili Automatic Speech Recognition ACL 2025 On the Trainability and Classical Simulability of Learning Matrix Product States Variationally AAAI 2025 On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures ICML 2025 On the Transferability of Causal Knowledge for Language Models NAACL 2025 On the Transfer of Object-Centric Representation Learning ICLR 2025 On the Utility of Equal Batch Sizes for Inference in Stochastic Gradient Descent JMLR 2025 On the Versatility of Sparse Autoencoders for In-Context Learning EMNLP 2025 On the Vulnerability of Text Sanitization NAACL 2025