{"total":39,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"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":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"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":"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":"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":"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":"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":"2401.15207","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","created":"2024-01-26","cited_by_count":12,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2401.09192","title":"Preparing Lessons for Progressive Training on Language Models","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2403.04978","title":"Stacking as Accelerated Gradient Descent","created":"2024-03-08","cited_by_count":5,"area":null},{"id":"2306.11903","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","created":"2023-06-20","cited_by_count":4,"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":"2508.08011","title":"Optimal Transport Depth Up-Scaling","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2504.04151","title":"STEP: Staged Parameter-Efficient Pre-training for Large Language Models","created":"2025-04-05","cited_by_count":2,"area":null},{"id":"2504.10735","title":"Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2509.03972","title":"Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"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":"2603.08647","title":"Grow, Don't Overwrite: Fine-tuning Without Forgetting","created":"2026-03-09","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":"2404.07999","title":"A Multi-Level Framework for Accelerating Training Transformer Models","created":"2024-04-07","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":"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":"2511.22362","title":"Efficient-Husformer: Efficient Multimodal Transformer Hyperparameter Optimization for Stress and Cognitive Loads","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2605.12106","title":"Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization","created":"2026-05-12","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":"2608.02829","title":"Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.30299","title":"Staged Depth Training: A Representation Curriculum for PINNs","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}