Machine Learning

On the Optimal Memorization Capacity of Transformers ICLR 2025 On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models ICLR 2025 On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena NAACL 2025 On the O(sqrt(d)/T^(1/4)) Convergence Rate of RMSProp and Its Momentum Extension Measured by l_1 Norm JMLR 2025 On the Out-Of-Distribution Generalization of Large Multimodal Models CVPR 2025 On the Out-of-Distribution Generalization of Self-Supervised Learning ICML 2025 On the Perception Bottleneck of VLMs for Chart Understanding EMNLP 2025 On the Performance Analysis of Momentum Method: A Frequency Domain Perspective ICLR 2025 On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond AISTATS 2025 On the Power of Multitask Representation Learning with Gradient Descent AISTATS 2025 On the Power of Optimism in Constrained Online Convex Optimization IJCAI 2025 On the Power of Strategic Corpus Enrichment in Content Creation Games AAAI 2025 On the Price of Differential Privacy for Hierarchical Clustering ICLR 2025 On the Privacy-preserving Generalized Eigenvalue Problem ACML 2025 On the Private Estimation of Smooth Transport Maps ICML 2025 On the Provable Importance of Gradients for Autonomous Language-Assisted Image Clustering ICCV 2025 On the Provable Separation of Scales in Maximal Update Parameterization ICML 2025 On the Query Complexity of Verifier-Assisted Language Generation ICML 2025 On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings ACL 2025 On the Relation between Trainability and Dequantization of Variational Quantum Learning Models ICLR 2025 On the Relationship Between Monotone and Squared Probabilistic Circuits AAAI 2025 On the Reliability of Large Language Models for Causal Discovery ACL 2025 On the Representation of Pairwise Causal Background Knowledge and Its Applications in Causal Inference JMLR 2025 On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs ACL 2025 On the Robust Approximation of ASR Metrics ACL 2025