{"total":68,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172,"area":null},{"id":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2405.15319","title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training","created":"2024-05-24","cited_by_count":43,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2305.02869","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2409.12903","title":"Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization","created":"2024-09-19","cited_by_count":29,"area":null},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22,"area":null},{"id":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2310.11451","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","created":"2023-10-17","cited_by_count":17,"area":null},{"id":"2406.17503","title":"WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2308.06103","title":"Composable Function-preserving Expansions for Transformer Architectures","created":"2023-08-11","cited_by_count":13,"area":null},{"id":"2504.13292","title":"Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model","created":"2025-04-17","cited_by_count":13,"area":null},{"id":"2505.05587","title":"Steepest Descent Density Control for Compact 3D Gaussian Splatting","created":"2025-05-08","cited_by_count":13,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2410.05357","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2410.23168","title":"TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters","created":"2024-10-30","cited_by_count":9,"area":null},{"id":"2406.06567","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","created":"2024-06-03","cited_by_count":7,"area":null},{"id":"2407.12665","title":"Beyond Next Token Prediction: Patch-Level Training for Large Language Models","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2602.16490","title":"From Growing to Looping: A Unified View of Iterative Computation in LLMs","created":"2026-02-18","cited_by_count":7,"area":null},{"id":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2512.08819","title":"Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2406.02469","title":"Landscape-Aware Growing: The Power of a Little LAG","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2506.11389","title":"Curriculum-Guided Layer Scaling for Language Model Pretraining","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2508.08011","title":"Optimal Transport Depth Up-Scaling","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2605.08297","title":"A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2511.11683","title":"Stratified Knowledge-Density Super-Network for Scalable Vision Transformers","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2603.07506","title":"A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2405.16287","title":"LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters","created":"2024-05-25","cited_by_count":1,"area":null},{"id":"2505.06699","title":"Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws","created":"2025-05-10","cited_by_count":1,"area":null},{"id":"2506.21329","title":"Active Inference AI Systems for Scientific Discovery","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2507.07129","title":"Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2511.04981","title":"Scaling depth capacity via zero/one-layer model expansion","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2604.04281","title":"Preservation Is Not Enough for Width Growth: Regime-Sensitive Selection of Dense LM Warm Starts","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2607.24887","title":"Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2402.12418","title":"Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures","created":"2024-02-19","cited_by_count":0,"area":null},{"id":"2404.07999","title":"A Multi-Level Framework for Accelerating Training Transformer Models","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2405.15895","title":"Manifold Metric: A Loss Landscape Approach for Predicting Model Performance","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2406.13450","title":"Federating to Grow Transformers with Constrained Resources without Model Sharing","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2408.11746","title":"Mixed Sparsity Training: Achieving 4$\\times$ FLOP Reduction for Transformer Pretraining","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2504.18590","title":"A multilevel approach to accelerate the training of Transformers","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.24241","title":"Advantageous Parameter Expansion Training Makes Better Large Language Models","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.09940","title":"Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","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":"2601.19694","title":"Self-Supervised Weight Templates for Scalable Vision Model Initialization","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.05909","title":"CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.07523","title":"Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.14769","title":"Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.19147","title":"Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.13405","title":"When is Warmstarting Effective for Scaling Language Models?","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.23656","title":"Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.16768","title":"Taming Curvature: Architecture Warm-Up for Stable Transformer Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.14571","title":"What Does Model Growth Really Add? Functional Capacity Beyond Parameter Count","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.02829","title":"Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.14664","title":"Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2610.01649","title":"CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16817","title":"Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}