arXiv:2509.05381v3 Announce Type: replace-cross Abstract: We study reinforcement learning from human feedback under misspecification. Sometimes human feedback is systematically wrong on certain types of inputs, like a broken compass that points the wrong way in specific regions. We prove that…
arXiv:2509.10516v1 Announce Type: new Abstract: The increasing digitalization of education presents unprecedented opportunities for data-driven personalization, yet it introduces significant student data privacy challenges. Conventional recommender systems rely on centralized data, a paradigm often incompatible with modern data protection regulations.…
arXiv:2509.11293v1 Announce Type: cross Abstract: The Lifshitz-Petrich (LP) model is a classical model for describing complex spatial patterns such as quasicrystals and multiphase structures. Solving and classifying the solutions of the LP model is challenging due to the presence of…
arXiv:2509.10517v1 Announce Type: new Abstract: Machine learning models hold significant potential for predicting in-hospital mortality, yet data privacy constraints and the statistical heterogeneity of real-world clinical data often hamper their development. Federated Learning (FL) offers a privacy-preserving solution, but its…
arXiv:2509.11511v1 Announce Type: cross Abstract: Class imbalance in supervised classification often degrades model performance by biasing predictions toward the majority class, particularly in critical applications such as medical diagnosis and fraud detection. Traditional oversampling techniques, including SMOTE and its variants,…
arXiv:2509.10518v1 Announce Type: new Abstract: We introduce the Holographic Knowledge Manifold (HKM), a four-phase pipeline that achieves zero catastrophic forgetting in AI knowledge representation while maintaining minimal memory growth and high efficiency. Leveraging fractal quantization, probabilistic entanglement, and dynamic diffraction…
arXiv:2509.11824v1 Announce Type: cross Abstract: Online AI platforms for creating music from text prompts (AI music), such as Suno and Udio, are now being used by hundreds of thousands of users. Some AI music is appearing in advertising, and even…
arXiv:2509.10519v1 Announce Type: new Abstract: Approximate multipliers (AppMults) are widely used in deep learning accelerators to reduce their area, delay, and power consumption. However, AppMults introduce arithmetic errors into deep learning models, necessitating a retraining process to recover accuracy. A…
arXiv:2509.12187v1 Announce Type: cross Abstract: Novel view synthesis (NVS) of in-the-wild garments is a challenging task due significant occlusions, complex human poses, and cloth deformations. Prior methods rely on synthetic 3D training data consisting of mostly unoccluded and static objects,…
arXiv:2509.10520v1 Announce Type: new Abstract: In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it difficult to isolate the effect of…
