{"total":178,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543,"area":"wm"},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161,"area":null},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"area":null},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2405.17399","title":"Transformers Can Do Arithmetic with the Right Embeddings","created":"2024-05-27","cited_by_count":78,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2501.10326","title":"Large language models for automated scholarly paper review: A survey","created":"2025-01-17","cited_by_count":61,"area":null},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60,"area":"moe"},{"id":"2303.01610","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","created":"2023-03-02","cited_by_count":59,"area":"moe"},{"id":"2206.00888","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","created":"2022-06-02","cited_by_count":51,"area":null},{"id":"2401.06199","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2410.20280","title":"MarDini: Masked Autoregressive Diffusion for Video Generation at Scale","created":"2024-10-26","cited_by_count":49,"area":"diffusion"},{"id":"2205.12654","title":"Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages","created":"2022-05-25","cited_by_count":48,"area":"distill"},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2206.01127","title":"VL-BEiT: Generative Vision-Language Pretraining","created":"2022-06-02","cited_by_count":39,"area":"mllm"},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"area":null},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"area":null},{"id":"2211.04508","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","created":"2022-11-08","cited_by_count":35,"area":null},{"id":"2304.09856","title":"LipsFormer: Introducing Lipschitz Continuity to Vision Transformers","created":"2023-04-19","cited_by_count":34,"area":null},{"id":"2304.14802","title":"ResiDual: Transformer with Dual Residual Connections","created":"2023-04-28","cited_by_count":31,"area":null},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28,"area":null},{"id":"2206.10139","title":"Insights into Pre-training via Simpler Synthetic Tasks","created":"2022-06-21","cited_by_count":26,"area":null},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"id":"2305.12972","title":"VanillaNet: the Power of Minimalism in Deep Learning","created":"2023-05-22","cited_by_count":23,"area":null},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2210.06423","title":"Foundation Transformers","created":"2022-10-12","cited_by_count":19,"area":null},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2211.06894","title":"Learning from partially labeled data for multi-organ and tumor segmentation","created":"2022-11-13","cited_by_count":18,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2410.01723","title":"HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration","created":"2024-10-02","cited_by_count":17,"area":"diffusion"},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2205.12216","title":"T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2206.00330","title":"B2T Connection: Serving Stability and Performance in Deep Transformers","created":"2022-06-01","cited_by_count":16,"area":null},{"id":"2412.02682","title":"The Asymptotic Behavior of Attention in Transformers","created":"2024-12-03","cited_by_count":16,"area":null},{"id":"2503.04598","title":"HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2409.12272","title":"Mastering Chess with a Transformer Model","created":"2024-09-18","cited_by_count":15,"area":null},{"id":"2203.02094","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","created":"2022-03-04","cited_by_count":14,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2506.22696","title":"Residual Matrix Transformers: Scaling the Size of the Residual Stream","created":"2025-06-28","cited_by_count":12,"area":null},{"id":"2305.15781","title":"VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale","created":"2023-05-25","cited_by_count":11,"area":"distill"},{"id":"2310.15777","title":"MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2601.21579","title":"KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2211.13184","title":"TorchScale: Transformers at Scale","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2305.08096","title":"Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation","created":"2023-05-14","cited_by_count":10,"area":"distill"},{"id":"2504.12463","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","created":"2025-04-16","cited_by_count":10,"area":"moe"},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2606.18524","title":"On the Residual Scaling of Looped Transformers: Stability and Transferability","created":"2026-06-16","cited_by_count":10,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2212.05956","title":"Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging","created":"2022-12-12","cited_by_count":9,"area":"distill"},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2505.21910","title":"Taming Transformer Without Using Learning Rate Warmup","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2512.16762","title":"NRGPT: An Energy-based Alternative for GPT","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2601.19895","title":"Post-LayerNorm Is Back: Stable, ExpressivE, and Deep","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2602.12078","title":"Tiny Recursive Reasoning with Mamba-2 Attention Hybrid","created":"2026-02-12","cited_by_count":7,"area":"lr"},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2605.18855","title":"Delta Attention Residuals","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2607.13491","title":"DeepLoop: Depth Scaling for Looped Transformers","created":"2026-07-15","cited_by_count":7,"area":null},{"id":"2305.02790","title":"BranchNorm: Robustly Scaling Extremely Deep Transformers","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2603.15619","title":"Mixture-of-Depths Attention","created":"2026-03-16","cited_by_count":6,"area":null},{"id":"2208.14111","title":"Transformers with Learnable Activation Functions","created":"2022-08-30","cited_by_count":5,"area":null},{"id":"2309.14136","title":"Masked Image Residual Learning for Scaling Deeper Vision Transformers","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2402.03317","title":"SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization","created":"2024-01-02","cited_by_count":5,"area":null},{"id":"2602.09009","title":"ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling","created":"2026-02-09","cited_by_count":5,"area":null},{"id":"2602.18308","title":"JPmHC Dynamical Isometry via Orthogonal Hyper-Connections","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2606.24898","title":"Dense Supervision Is Not Enough: The Readout Blind Spot in Looped Language Models","created":"2026-06-12","cited_by_count":5,"area":null},{"id":"2205.10505","title":"A Study on Transformer Configuration and Training Objective","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2410.05052","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2411.03042","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","created":"2024-11-05","cited_by_count":4,"area":null},{"id":"2501.08570","title":"Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2602.10408","title":"Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2603.06603","title":"Scale Dependent Data Duplication","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.26895","title":"Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models","created":"2026-05-26","cited_by_count":4,"area":null},{"id":"2607.14530","title":"xHC: Expanded Hyper-Connections","created":"2026-07-16","cited_by_count":4,"area":"moe"},{"id":"2211.13527","title":"Beyond Mahalanobis-Based Scores for Textual OOD Detection","created":"2022-11-24","cited_by_count":3,"area":null}],"next_cursor":"100"}