{"total":30,"rows":[{"id":"2603.25040","title":"Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale","created":"2026-03-26","cited_by_count":29,"area":null},{"id":"2512.12167","title":"Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings","created":"2025-12-13","cited_by_count":26,"area":null},{"id":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2604.20817","title":"Convergent Evolution: How Different Language Models Learn Similar Number Representations","created":"2026-04-22","cited_by_count":6,"area":null},{"id":"2505.13027","title":"Deconstructing Positional Information: From Attention Logits to Training Biases","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2503.08239","title":"EnergyFormer: Energy Attention with Fourier Embedding for Hyperspectral Image Classification","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2601.22181","title":"MrRoPE: Mixed-radix Rotary Position Embedding","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2505.01475","title":"CodeSSM: Towards State Space Models for Code Understanding","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2601.00919","title":"Attention Needs to Focus: A Unified Perspective on Attention Allocation","created":"2026-01-01","cited_by_count":3,"area":null},{"id":"2506.13277","title":"SeqPE: Transformer with Sequential Position Encoding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2512.07525","title":"Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2606.12146","title":"nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2607.07678","title":"How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2508.18308","title":"CoPE: A Lightweight Complex Positional Encoding","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2602.06774","title":"Towards Understanding What State Space Models Learn About Code","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2604.07522","title":"Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.10706","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2504.04238","title":"Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2508.19167","title":"Beyond flattening: a geometrically principled positional encoding for vision transformers with Weierstrass elliptic functions","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.16629","title":"Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2512.22378","title":"Towards Efficient Post-Training via Fourier-Driven Adapter Architectures","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2601.06113","title":"Towards Infinite Length Extrapolation: A Unified Approach","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2603.11680","title":"UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.05913","title":"Wisteria: A Unified Multi-Scale Feature Learning Framework for DNA Language Model","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23719","title":"Weierstrass Positional Encoding for Vision Transformers","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.21405","title":"Anti-Periodic Positional Encoding: M\\\"obius Boundary Conditions Make In-Context Retrieval Reliable","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.29715","title":"Higher-Dimensional Rotary Position Embedding","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.34556","title":"RoPE is Dead, Long Live RoPE: Towards Scalable Data-aware Positional Encodings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.06963","title":"WavePrune: One period is often enough for RoPE","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}