Theory

QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs ACL 2026 Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent JMLR 2026 Rethinking Data Mixing from the Perspective of Large Language Models ACL 2026 Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning ACL 2026 Scaling Laws for Code: A More Data-Hungry Regime ACL 2026 SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization WACV 2026 Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Feature Learning by Learnable Channel Attention ALT 2026 Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse ACL 2026 Statistical Learning Theory for Neural Operators JMLR 2026 The Drift Kernel: Why Diffusion Models Change Even When Told Not To CVPR 2026 The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network COLT 2026 Theoretical Compression Bounds for Wide Multilayer Perceptrons COLT 2026 Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective JMLR 2026 Tunable Soft Equivariance with Guarantees CVPR 2026 Understanding and Enforcing Weight Disentanglement in Task Arithmetic CVPR 2026 Why "Classic" Transformers Are Shallow and A Depth-Enabling Technique JMLR 2026 Why Do More Experts Fail? A Theoretical Analysis of Model Merging ACL 2026 Activation Subspaces for Out-of-Distribution Detection ICCV 2025 Almost Sure Convergence of Dropout Algorithms for Neural Networks JMLR 2025 Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods ICLR 2025 Analyzing and Modeling LLM Response Lengths with Extreme Value Theory: Anchoring Effects and Hybrid Distributions EMNLP 2025 A Priori Estimation of the Approximation, Optimization and Generalization Errors of Random Neural Networks for Solving Partial Differential Equations IJCAI 2025 A Theoretical Analysis of Self-Supervised Learning for Vision Transformers ICLR 2025 A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning AISTATS 2025 Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey ACL 2025