Theory

Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nyström Method AAAI 2025 Circuit Complexity Bounds for RoPE-based Transformer Architecture EMNLP 2025 Circuit Stability Characterizes Language Model Generalization ACL 2025 Circuit-Tracer: A New Library for Finding Feature Circuits EMNLP 2025 Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models ICLR 2025 Compute Optimal Scaling of Skills: Knowledge vs Reasoning ACL 2025 Confounding Factors in Relating Model Performance to Morphology EMNLP 2025 Contrasting Adversarial Perturbations: The Space of Harmless Perturbations AAAI 2025 Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025 Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models AAAI 2025 Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025 Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls EMNLP 2025 DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments AAAI 2025 Differential Privacy Mechanisms in Neural Tangent Kernel Regression WACV 2025 Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding ACL 2025 Do ImageNet-trained Models Learn Shortcuts? The Impact of Frequency Shortcuts on Generalization CVPR 2025 DRM Revisited: A Complete Error Analysis JMLR 2025 Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations AISTATS 2025 Emergence of meta-stable clustering in mean-field transformer models ICLR 2025 Enhancing Implicit Neural Representations via Symmetric Power Transformation AAAI 2025 Equivariant Manifold Neural ODEs and Differential Invariants JMLR 2025 Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025 Explainable Neural Networks with Guarantee: A Sparse Estimation Approach AAAI 2025 Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint IJCAI 2025 Expressive Power of Temporal Message Passing AAAI 2025