Learning Theory

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods ICLR 2025 Towards Fundamental Limits for Active Multi-distribution Learning COLT 2025 Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification ICLR 2025 Towards Improved Risk Bounds for Transductive Learning IJCAI 2025 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025 Towards Memorization Estimation: Fast, Formal and Free ICML 2025 Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks ICML 2025 Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin JMLR 2025 Towards Understanding Parametric Generalized Category Discovery on Graphs ICML 2025 Towards Understanding the Universality of Transformers for Next-Token Prediction ICLR 2025 Toward Understanding In-context vs. In-weight Learning ICLR 2025 To What Extent Can In-Context Learning Solve Unseen Tasks? IJCNLP 2025 Trade-offs in Data Memorization via Strong Data Processing Inequalities COLT 2025 Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions ICML 2025 Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning ACL 2025 Training One-Dimensional Graph Neural Networks is NP-Hard ICLR 2025 Training on the Benchmark Is Not All You Need AAAI 2025 Training on the Test Task Confounds Evaluation and Emergence ICLR 2025 Trajectory-Dependent Generalization Bounds for Pairwise Learning with φ-mixing Samples IJCAI 2025 Transferable Relativistic Predictor: Mitigating Cross-Task Cold-Start Issue in NAS IJCAI 2025 Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought ICLR 2025 Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow ICLR 2025 Transformers Provably Solve Parity Efficiently with Chain of Thought ICLR 2025 Trick or Neat: Adversarial Ambiguity and Language Model Evaluation ACL 2025 Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems EMNLP 2025