{"total":40,"rows":[{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2501.15891","title":"Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks","created":"2025-01-27","cited_by_count":63,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34,"area":null},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23,"area":null},{"id":"2406.10322","title":"LieRE: Lie Rotational Positional Encodings","created":"2024-06-14","cited_by_count":18,"area":null},{"id":"2410.21216","title":"HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2502.11075","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","created":"2025-02-16","cited_by_count":14,"area":null},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2504.00927","title":"Multi-Token Attention","created":"2025-04-01","cited_by_count":10,"area":null},{"id":"2509.05218","title":"HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2506.07405","title":"RiemannFormer: A Framework for Attention in Curved Spaces","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","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":"2411.12901","title":"Signformer is all you need: Towards Edge AI for Sign Language","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2505.09466","title":"A 2D Semantic-Aware Position Encoding for Vision Transformers","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2407.04899","title":"Algorithmic Language Models with Neurally Compiled Libraries","created":"2024-07-06","cited_by_count":2,"area":null},{"id":"2503.08067","title":"Context-aware Biases for Length Extrapolation","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2506.09342","title":"Latent Multi-Head Attention for Small Language Models","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2512.04963","title":"GeoPE:A Unified Geometric Positional Embedding for Structured Tensors","created":"2025-12-04","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":"2406.08272","title":"Learning interpretable positional encodings in transformers depends on initialization","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2501.13428","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2503.23174","title":"TRA: Better Length Generalisation with Threshold Relative Attention","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2607.10134","title":"LeRoPE: Learnable RoPE Frequencies Improve Language Modeling","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2410.11150","title":"Optimizing Encoder-Only Transformers for Session-Based Recommendation Systems","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2412.10446","title":"Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2507.11768","title":"LLMs are Bayesian, In Expectation, Not in Realization","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.13766","title":"NDLPNet: A Location-Aware Nighttime Deraining Network and a Real-World Benchmark Dataset","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2511.19279","title":"MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2602.01865","title":"GRAB: An LLM-Inspired Sequence-First Click-Through Rate Prediction Modeling Paradigm","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.14430","title":"Three-Phase Transformer","created":"2026-04-15","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":"2605.30022","title":"Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.31067","title":"Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.07314","title":"Content-Based Addressing for Long Context","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.20278","title":"Labeled Incidence Structures for Native Transformer Modeling of Text, Knowledge Graphs, and Hypergraphs","created":"2026-07-29","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}],"next_cursor":null}