Theory

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent ICLR 2025 Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint ICML 2025 Improving Generalization of Deep Neural Networks by Optimum Shifting AAAI 2025 Improving Neural Optimal Transport via Displacement Interpolation ICLR 2025 Inapproximability of Optimal Multi-Agent Pathfinding Problems AAAI 2025 In Benchmarks We Trust ... Or Not? EMNLP 2025 Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving ICLR 2025 Influence Functions for Scalable Data Attribution in Diffusion Models ICLR 2025 Information-Theoretic Guarantees for Recovering Low-Rank Tensors from Symmetric Rank-One Measurements ALT 2025 Input Space Mode Connectivity in Deep Neural Networks ICLR 2025 Instability, Computational Efficiency and Statistical Accuracy JMLR 2025 Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Survey IJCAI 2025 Intrinsic Test of Unlearning Using Parametric Knowledge Traces EMNLP 2025 Is Incremental Structure Prediction Process Universal across Languages?: Revisiting Parsing Strategy through Speculation CoNLL 2025 Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness NAACL 2025 Is Your LLM Outdated? A Deep Look at Temporal Generalization NAACL 2025 Iterated Belief Change as Learning IJCAI 2025 Joint Scoring Rules: Competition Between Agents Avoids Performative Prediction AAAI 2025 Knockoffs Inference for Partially Linear Models with Automatic Structure Discovery AAAI 2025 KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks ICLR 2025 Lambda-Skip Connections: the architectural component that prevents Rank Collapse ICLR 2025 Language Models Are Implicitly Continuous ICLR 2025 Language Models Encode the Value of Numbers Linearly COLING 2025 Language Models Resist Alignment: Evidence From Data Compression ACL 2025 Large Language Model Evaluation via Matrix Nuclear-Norm EMNLP 2025