{"total":31,"rows":[{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"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":"2507.19595","title":"Efficient Attention Mechanisms for Large Language Models: A Survey","created":"2025-07-25","cited_by_count":22,"area":null},{"id":"2504.08719","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","created":"2025-04-11","cited_by_count":19,"area":null},{"id":"2603.11510","title":"Tiny Aya: Bridging Scale and Multilingual Depth","created":"2026-03-12","cited_by_count":15,"area":null},{"id":"2506.15545","title":"RATTENTION: Towards the Minimal Sliding Window Size in Local-Global Attention Models","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2605.15514","title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2511.11579","title":"Decoupling Positional and Symbolic Attention Behavior in Transformers","created":"2025-10-03","cited_by_count":6,"area":null},{"id":"2602.16837","title":"A Structural Theory of Position Bias in Transformers","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2512.14391","title":"RePo: Language Models with Context Re-Positioning","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2603.11611","title":"Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2511.08368","title":"A Circular Argument : Does RoPE need to be Equivariant for Vision?","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2602.03681","title":"Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2603.06591","title":"What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs","created":"2026-02-04","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":"2509.16278","title":"Language Modeling with Learned Meta-Tokens","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2605.09877","title":"Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2608.11909","title":"Disentangling the Expressivity of RoPE","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2602.01845","title":"No Generation without Representation: Efficient Causal Protein Language Models Enable Zero-Shot Fitness Estimation","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.14050","title":"Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2604.18603","title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.24715","title":"Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.21249","title":"Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2608.10296","title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","created":"2026-08-10","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":"2609.33268","title":"LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models","created":"2026-09-27","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":"2609.38530","title":"Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17191","title":"FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}