{"total":70,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"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":"2203.06311","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","created":"2022-03-12","cited_by_count":70,"area":null},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"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":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"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":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"area":null},{"id":"2307.00360","title":"BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformer","created":"2023-07-01","cited_by_count":23,"area":null},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"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":"2409.19044","title":"On the Inductive Bias of Stacking Towards Improving Reasoning","created":"2024-09-27","cited_by_count":19,"area":"lr"},{"id":"2305.08702","title":"Recyclable Tuning for Continual Pre-training","created":"2023-05-15","cited_by_count":17,"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":"2401.01543","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","created":"2024-01-03","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":"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":"2405.14132","title":"Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization","created":"2024-05-23","cited_by_count":10,"area":"diffusion"},{"id":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","cited_by_count":10,"area":"moe"},{"id":"2410.23168","title":"TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters","created":"2024-10-30","cited_by_count":9,"area":null},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"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":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2508.02751","title":"SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference","created":"2025-08-03","cited_by_count":6,"area":"inference"},{"id":"2410.00350","title":"Efficient Training of Large Vision Models via Advanced Automated Progressive Learning","created":"2024-09-06","cited_by_count":5,"area":"diffusion"},{"id":"2406.02469","title":"Landscape-Aware Growing: The Power of a Little LAG","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2511.06016","title":"One-Shot Knowledge Transfer for Scalable Person Re-Identification","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2602.02472","title":"SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning","created":"2026-02-02","cited_by_count":4,"area":"moe"},{"id":"2211.06840","title":"FPT: Improving Prompt Tuning Efficiency via Progressive Training","created":"2022-11-13","cited_by_count":3,"area":null},{"id":"2312.16486","title":"PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion","created":"2023-12-27","cited_by_count":3,"area":"diffusion"},{"id":"2501.05313","title":"Optimizing Distributed Deployment of Mixture-of-Experts Model Inference in Serverless Computing","created":"2025-01-09","cited_by_count":3,"area":"moe"},{"id":"2505.20155","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2309.10066","title":"Automatic Personalized Impression Generation for PET Reports Using Large Language Models","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2404.00672","title":"A General and Efficient Training for Transformer via Token Expansion","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2508.01167","title":"T2S: Tokenized Skill Scaling for Lifelong Imitation Learning","created":"2025-08-02","cited_by_count":2,"area":"offlinerl"},{"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":"2607.16568","title":"Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs","created":"2026-07-18","cited_by_count":2,"area":null},{"id":"2306.08756","title":"Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2510.06502","title":"GUIDE: Guided Initialization and Distillation of Embeddings","created":"2025-10-07","cited_by_count":1,"area":"distill"},{"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":"2602.11081","title":"SteuerLLM: Local specialized large language model for German tax law analysis","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"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":"2604.12391","title":"Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2608.27367","title":"Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models","created":"2026-08-27","cited_by_count":1,"area":"wm"},{"id":"2306.06190","title":"$FastDoc$: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy","created":"2023-06-09","cited_by_count":0,"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":"2406.13450","title":"Federating to Grow Transformers with Constrained Resources without Model Sharing","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2408.08681","title":"A Mean Field Ansatz for Zero-Shot Weight Transfer","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2410.04140","title":"Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher","created":"2024-10-05","cited_by_count":0,"area":"distill"},{"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":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","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":"2604.00489","title":"Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling","created":"2026-04-01","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":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","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":"2609.13545","title":"Runtime-Incremental Transformer for Reinforcement-Learning-Based Adaptive Control","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.37631","title":"Procedural Core: A Compact Recurrent Initialization for Vision Transformers","created":"2026-09-29","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}],"next_cursor":null}