{"total":18,"rows":[{"id":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52,"area":null},{"id":"2504.16318","title":"Semantics at an Angle: When Cosine Similarity Works Until It Doesn't","created":"2025-04-22","cited_by_count":13,"area":null},{"id":"2310.15921","title":"Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2406.10984","title":"Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2501.15754","title":"Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference","created":"2025-01-27","cited_by_count":5,"area":null},{"id":"2604.07569","title":"Learning is Forgetting: LLM Training As Lossy Compression","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2411.16252","title":"NormXLogit: The Head-on-Top Never Lies","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2411.00680","title":"Zipfian Whitening","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2604.08764","title":"Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2409.11253","title":"Norm of Mean Contextualized Embeddings Determines their Variance","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2506.22881","title":"CLIP-like Model as a Foundational Density Ratio Estimator","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2602.10908","title":"SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.13911","title":"On the Tip of the Tongue: Why LLMs Hallucinate Answers They Can Decode","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.12281","title":"What makes a word hard to learn? Modeling L1 influence on English vocabulary difficulty","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.16461","title":"Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.21139","title":"PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.30625","title":"Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.36670","title":"FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}