{"total":40,"rows":[{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"area":null},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","cited_by_count":80,"area":null},{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2405.18781","title":"On the Role of Attention Masks and LayerNorm in Transformers","created":"2024-05-29","cited_by_count":48,"area":null},{"id":"2306.17759","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","created":"2023-06-30","cited_by_count":47,"area":null},{"id":"2402.10198","title":"SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2403.11561","title":"Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection","created":"2024-03-18","cited_by_count":19,"area":null},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2305.18399","title":"On the impact of activation and normalization in obtaining isometric embeddings at initialization","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2505.01996","title":"Always Skip Attention","created":"2025-05-04","cited_by_count":13,"area":null},{"id":"2404.08634","title":"When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2602.02551","title":"EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis","created":"2026-01-30","cited_by_count":9,"area":null},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2510.00345","title":"Cutting the Skip: Training Residual-Free Transformers","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2512.14366","title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","created":"2025-12-16","cited_by_count":8,"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":"2408.09624","title":"Attention is a smoothed cubic spline","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2410.10609","title":"Lambda-Skip Connections: the architectural component that prevents Rank Collapse","created":"2024-10-14","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":"2605.25880","title":"The Quantization Benefits of Residual-Free Transformers","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2312.08937","title":"BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomials","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2410.09637","title":"ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2503.22547","title":"Bridging the Dimensional Chasm: Uncover Layer-wise Dimensional Reduction in Transformers through Token Correlation","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2510.23912","title":"Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2312.06182","title":"Why \"classic\" Transformers are shallow and how to make them go deep","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2504.18929","title":"Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2511.20698","title":"On the Role of Hidden States of Modern Hopfield Network in Transformer","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.05996","title":"Orthogonal Self-Attention","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2404.12362","title":"KV-weights are all you need for skipless transformers","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2511.03270","title":"SCALE: Upscaled Continual Learning of Large Language Models","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2605.07588","title":"Revisiting Transformer Layer Parameterization Through Causal Energy Minimization","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}