{"total":19,"rows":[{"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":"2312.05614","title":"Transformer as Linear Expansion of Learngene","created":"2023-12-09","cited_by_count":13,"area":null},{"id":"2401.08139","title":"Transferring Core Knowledge via Learngenes","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2408.07337","title":"KIND: Knowledge Integration and Diversion for Training Decomposable Models","created":"2024-08-14","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":"2511.06016","title":"One-Shot Knowledge Transfer for Scalable Person Re-Identification","created":"2025-11-08","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":"2605.08146","title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2412.19417","title":"KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2605.07271","title":"Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2512.09796","title":"Knowledge Diversion for Efficient Morphology Control and Policy Transfer","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2504.19103","title":"Harmonizing Generalization and Personalization in Ring-topology Decentralized Federated Learning","created":"2025-04-27","cited_by_count":0,"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":"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":"2605.07783","title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08209","title":"Learngene Search Across Multiple Datasets for Building Variable-Sized Models","created":"2026-05-06","cited_by_count":0,"area":null}],"next_cursor":null}