Similar Items: Geometric Factual Recall in Transformers
- Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
- From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
- Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
- Characterizing the Expressivity of Local Attention in Transformers
- Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
- Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators