{"total":29,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"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":"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":"2308.06103","title":"Composable Function-preserving Expansions for Transformer Architectures","created":"2023-08-11","cited_by_count":13,"area":null},{"id":"2407.02783","title":"52B to 1T: Lessons Learned via Tele-FLM Series","created":"2024-07-03","cited_by_count":11,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"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":"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":"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":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"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":"2501.12486","title":"The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws","created":"2025-01-21","cited_by_count":2,"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":"2508.06309","title":"Matrix-Driven Identification and Reconstruction of LLM Weight Homology","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","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":"2408.08681","title":"A Mean Field Ansatz for Zero-Shot Weight Transfer","created":"2024-08-16","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":"2511.03270","title":"SCALE: Upscaled Continual Learning of Large Language Models","created":"2025-11-05","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":"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":"2608.13277","title":"Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.16409","title":"SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}