{"total":29,"rows":[{"id":"2403.19243","title":"Efficient Learning With Sine-Activated Low-rank Matrices","created":"2024-03-28","cited_by_count":22,"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":"2407.10366","title":"Accessing Vision Foundation Models via ImageNet-1K","created":"2024-07-15","cited_by_count":10,"area":null},{"id":"2601.21725","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2404.16897","title":"Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models","created":"2024-04-25","cited_by_count":9,"area":null},{"id":"2510.00345","title":"Cutting the Skip: Training Residual-Free Transformers","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"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":"2404.06773","title":"Adapting LLaMA Decoder to Vision Transformer","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2410.07081","title":"JPEG Inspired Deep Learning","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2410.18352","title":"FedBaF: Federated Learning Aggregation Biased by a Foundation Model","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2412.16751","title":"The Master Key Filters Hypothesis: Deep Filters Are General","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2504.10231","title":"A Model Zoo of Vision Transformers","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2605.07191","title":"Attention Transfer Is Not Universally Effective for Vision Transformers","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2405.13901","title":"Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2503.09662","title":"CoRe^2: Collect, Reflect and Refine to Generate Better and Faster","created":"2025-03-12","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":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.00418","title":"Making Transformers Logical","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2506.05641","title":"Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2509.04442","title":"Delta Activations: A Representation for Finetuned Large Language Models","created":"2025-09-04","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":"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":"2609.07086","title":"Conditioned Initialization for Attention","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.35745","title":"Copy the Same, Distill the Difference: Initializing Linear Vision Transformers","created":"2026-09-28","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}