{"total":181,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"area":null},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320,"area":null},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"area":null},{"id":"2106.09553","title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","created":"2021-06-17","cited_by_count":206,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2107.02988","title":"SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers","created":"2021-07-07","cited_by_count":169,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137,"area":null},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136,"area":null},{"id":"2102.08473","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","created":"2021-02-16","cited_by_count":126,"area":null},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126,"area":null},{"id":"2308.16137","title":"LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models","created":"2023-08-30","cited_by_count":124,"area":null},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118,"area":null},{"id":"2101.02402","title":"Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs","created":"2021-01-07","cited_by_count":110,"area":null},{"id":"2110.02544","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","created":"2021-10-06","cited_by_count":108,"area":null},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2104.09125","title":"SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization","created":"2021-04-19","cited_by_count":59,"area":null},{"id":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57,"area":null},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"area":null},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51,"area":null},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50,"area":null},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","cited_by_count":47,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2105.15168","title":"MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens","created":"2021-05-31","cited_by_count":46,"area":null},{"id":"2301.06568","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2105.04090","title":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE","created":"2021-05-10","cited_by_count":40,"area":null},{"id":"2104.08698","title":"A Simple and Effective Positional Encoding for Transformers","created":"2021-04-18","cited_by_count":37,"area":null},{"id":"2105.08399","title":"Relative Positional Encoding for Transformers with Linear Complexity","created":"2021-05-18","cited_by_count":37,"area":null},{"id":"2107.02561","title":"Rethinking Positional Encoding","created":"2021-07-06","cited_by_count":37,"area":null},{"id":"2201.12674","title":"Rewiring with Positional Encodings for Graph Neural Networks","created":"2022-01-29","cited_by_count":36,"area":null},{"id":"2307.14995","title":"TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer","created":"2023-07-27","cited_by_count":34,"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":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"area":null},{"id":"2204.11046","title":"Decoupled Side Information Fusion for Sequential Recommendation","created":"2022-04-23","cited_by_count":30,"area":null},{"id":"2203.01824","title":"LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2302.13840","title":"Target-Aware Tracking with Long-term Context Attention","created":"2023-02-27","cited_by_count":27,"area":null},{"id":"2105.04297","title":"How could Neural Networks understand Programs?","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26,"area":null},{"id":"2303.06337","title":"AutoMLP: Automated MLP for Sequential Recommendations","created":"2023-03-11","cited_by_count":25,"area":null},{"id":"2106.01950","title":"The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models","created":"2021-06-03","cited_by_count":23,"area":null},{"id":"2412.07237","title":"ArtFormer: Controllable Generation of Diverse 3D Articulated Objects","created":"2024-12-10","cited_by_count":22,"area":null},{"id":"2110.05841","title":"Relative Molecule Self-Attention Transformer","created":"2021-10-12","cited_by_count":21,"area":null},{"id":"2307.06235","title":"Multimodal Molecular Pretraining via Modality Blending","created":"2023-07-12","cited_by_count":21,"area":null},{"id":"2204.06644","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2402.04779","title":"StableMask: Refining Causal Masking in Decoder-only Transformer","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2104.07204","title":"Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2111.01353","title":"Can Vision Transformers Perform Convolution?","created":"2021-11-02","cited_by_count":18,"area":null},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2210.12574","title":"The Curious Case of Absolute Position Embeddings","created":"2022-10-23","cited_by_count":17,"area":null},{"id":"2306.11167","title":"Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset","created":"2023-06-19","cited_by_count":17,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2205.08987","title":"Trading Positional Complexity vs. Deepness in Coordinate Networks","created":"2022-05-18","cited_by_count":16,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2108.05064","title":"Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding","created":"2021-08-11","cited_by_count":14,"area":null},{"id":"2502.12370","title":"Positional Encoding in Transformer-Based Time Series Models: A Survey","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2505.12629","title":"Enhancing Latent Computation in Transformers with Latent Tokens","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2407.05388","title":"Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis","created":"2024-07-07","cited_by_count":12,"area":null},{"id":"2106.05505","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2107.12600","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","created":"2021-07-27","cited_by_count":11,"area":null},{"id":"2310.00576","title":"GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length","created":"2023-10-01","cited_by_count":11,"area":null},{"id":"2205.13425","title":"Do we really need temporal convolutions in action segmentation?","created":"2022-05-26","cited_by_count":10,"area":null},{"id":"2302.02060","title":"Representation Deficiency in Masked Language Modeling","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","cited_by_count":10,"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":"2503.09493","title":"Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection","created":"2025-03-12","cited_by_count":10,"area":null},{"id":"2204.03243","title":"Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators","created":"2022-04-07","cited_by_count":9,"area":null},{"id":"2211.04963","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"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":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8,"area":null},{"id":"2102.09206","title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder","created":"2021-02-18","cited_by_count":7,"area":null},{"id":"2303.11117","title":"EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2306.09114","title":"Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2404.02392","title":"Low-resource neural machine translation with morphological modeling","created":"2024-04-03","cited_by_count":7,"area":null},{"id":"2206.06460","title":"MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning","created":"2022-06-13","cited_by_count":6,"area":null},{"id":"2208.08643","title":"Learning Program Representations with a Tree-Structured Transformer","created":"2022-08-18","cited_by_count":6,"area":null},{"id":"2305.02086","title":"Revisiting the Encoding of Satellite Image Time Series","created":"2023-05-03","cited_by_count":6,"area":null}],"next_cursor":"100"}