Theory

Tokenisation is NP-Complete ACL 2025 TopoDiffusionNet: A Topology-aware Diffusion Model ICLR 2025 Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation ICLR 2025 Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs ICLR 2025 TorchCP: A Python Library for Conformal Prediction JMLR 2025 Toward Interpretable Time Series Modeling: A Kernel Representation Perspective IJCAI 2025 Towards a Complete Logical Framework for GNN Expressiveness ICLR 2025 Towards a Principled Evaluation of Knowledge Editors ACL 2025 Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective ICLR 2025 Towards Generalizable Neural Simulators: Addressing Distribution Shifts Induced by Environmental and Temporal Variations IJCAI 2025 Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey EMNLP 2025 Towards Improved Risk Bounds for Transductive Learning IJCAI 2025 Towards Memorization Estimation: Fast, Formal and Free ICML 2025 Towards Neural Scaling Laws for Time Series Foundation Models ICLR 2025 Towards Runtime Analysis of Population-Based Co-evolutionary Algorithms on Sparse Binary Zero-Sum Game AAAI 2025 Towards the Law of Capacity Gap in Distilling Language Models ACL 2025 Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks ICML 2025 Training One-Dimensional Graph Neural Networks is NP-Hard ICLR 2025 Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning ICLR 2025 Transformers are Universal In-context Learners ICLR 2025 Transformers Learn Low Sensitivity Functions: Investigations and Implications ICLR 2025 TRENDy: Temporal Regression of Effective Nonlinear Dynamics ICLR 2025 Tuning Frequency Bias of State Space Models ICLR 2025 Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation AAAI 2025 UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models ICLR 2025